Back
Profile
Flawlessdevstudio
Website
flawlessdev.comNumber of employees
Not specified
Locations
United States
Markets
Description
Flawless is a cutting-edge blockchain development studio bridging the gap between Web 2.0 & Web3, providing a full list of services and utilities for turning your Idea into disruptive, flexible, and modern technology. Contact Us. ... Our team is passionate about utilizing our technical capabilities and industry experience to help our clients extract real value by implementing Web 3.0 technologies across their organizations
Preferred payment options
Flawlessdevstudio
Research Scientist Intern - Audio to Mouth Synthesis
Santa Monica, USA
Santa Monica, USA
Full time
Office
Flawless, an innovative AI company highly recognized in the entertainment industry, is revolutionizing traditional filmmaking through its cutting-edge Gen AI film editing tools. Our goal is to equip filmmakers with advanced technology that fosters limitless creativity, broadens storytelling horizons, and delivers unmatched visual and emotional experiences.
Job Requirements: We are in search of an intern for a 4-6 month program with a focus on audio-visual synthesis, specifically concentrated on lip motion synthesis and head movement using diffusion-based techniques. The ideal candidate should be a Ph.D. student, preferably with experience in virtual talking heads or emotion-based talking synthesis models. The critical responsibilities include conducting independent research and developing algorithms adept at translating input audio into synchronized visual outputs. Candidates should possess expertise in training diffusion models, particularly in image synthesis, and a familiarity with technologies that animate emotions in videos. While prior publications are not mandatory, practical experience in these areas is highly valued.
Necessary Qualifications:
Synthesize lip motion and head movement from audio input through diffusion-based methods.
Conduct independent research to create algorithms incorporating advancements in audio-visual synthesis.
Collaborate in a progressive research environment to contribute to pioneering advancements in the field.
Proficiency in training diffusion models, particularly in image synthesis.
Knowledge of emotion animation technologies utilized in projects like 'emote video alive'.
Preferably Ph.D. candidates, though applicants with relevant experience and qualifications are encouraged.
Research background with demonstrated publication history in top-tier conferences on computer vision/graphics and deep learning like ECCV, ICCV, CVPR, and SIGGRAPH.
Salary Range: $6,000 - $7,000 per month
Flawless is dedicated to fostering an equal opportunity, safe workspace where individuals can excel. We are committed to providing fair employment opportunities irrespective of characteristics such as race, color, ancestry, religion, gender, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. Furthermore, qualified candidates will be considered based on merit, regardless of any past criminal records, in accordance with legal provisions.
Job Requirements: We are in search of an intern for a 4-6 month program with a focus on audio-visual synthesis, specifically concentrated on lip motion synthesis and head movement using diffusion-based techniques. The ideal candidate should be a Ph.D. student, preferably with experience in virtual talking heads or emotion-based talking synthesis models. The critical responsibilities include conducting independent research and developing algorithms adept at translating input audio into synchronized visual outputs. Candidates should possess expertise in training diffusion models, particularly in image synthesis, and a familiarity with technologies that animate emotions in videos. While prior publications are not mandatory, practical experience in these areas is highly valued.
Necessary Qualifications:
Synthesize lip motion and head movement from audio input through diffusion-based methods.
Conduct independent research to create algorithms incorporating advancements in audio-visual synthesis.
Collaborate in a progressive research environment to contribute to pioneering advancements in the field.
Proficiency in training diffusion models, particularly in image synthesis.
Knowledge of emotion animation technologies utilized in projects like 'emote video alive'.
Preferably Ph.D. candidates, though applicants with relevant experience and qualifications are encouraged.
Research background with demonstrated publication history in top-tier conferences on computer vision/graphics and deep learning like ECCV, ICCV, CVPR, and SIGGRAPH.
Salary Range: $6,000 - $7,000 per month
Flawless is dedicated to fostering an equal opportunity, safe workspace where individuals can excel. We are committed to providing fair employment opportunities irrespective of characteristics such as race, color, ancestry, religion, gender, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. Furthermore, qualified candidates will be considered based on merit, regardless of any past criminal records, in accordance with legal provisions.
Flawlessdevstudio
Research Scientist Intern - Multi-Modal Gesture Synthesis
Santa Monica, USA
Santa Monica, USA
Full time
Office
A prominent AI company based in Hollywood, Flawless, is revolutionizing traditional filmmaking with its innovative suite of Gen AI film editing tools. The company is dedicated to equipping filmmakers with state-of-the-art technology that fosters limitless creativity, expands storytelling horizons, and delivers extraordinary visual and emotional experiences.
Key Responsibilities:
Flawless is in search of a Multi-Modal Gesture Synthesis Research Intern to join the team in Santa Monica for a 3-6 month internship. The role entails focusing on Multi-Modal Gesture Synthesis and involves designing algorithms to create 3D body motion from audio-video input. Responsibilities include full body motion reconstruction, neural rendering using diffusion model-based methods, and managing body animation with 3D body models. The ideal candidate should have prior experience in body-related work, proficiency in 3DMMs and GANs, and at least one publication in the field of full body synthesis. Reporting to supervisors in Applied Science and Research Science departments, the candidate should hold a PhD in Computer Vision or Graphics.
Requirements:
Must be a PhD student specializing in Computer Vision or Graphics.
Ability to process audio-video inputs for predicting 3D body motion.
Conduct full body motion reconstruction in real-world settings.
Proficient in body animation involving 3D body models.
Experienced in utilizing diffusion model-based methods for advanced modeling.
Design algorithms to generate precise outputs from audio-video inputs.
Engage in neural rendering processes to enhance visual results.
Proficiency in body-related work.
Familiarity with 3D Morphable Models (3DMMs) and Generative Adversarial Networks (GANs).
Knowledge working with diffusion models.
Must have at least one publication related to full body synthesis at conferences like ECCV, ICCV, CVPR, or SIGGRAPH.
Salary: $6,000 - $7,000 per month
Flawless promotes an inclusive and safe work environment where individuals can excel. The company is committed to providing equal employment opportunities irrespective of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. Qualified applicants will be considered regardless of their criminal history, in line with legal regulations.
Key Responsibilities:
Flawless is in search of a Multi-Modal Gesture Synthesis Research Intern to join the team in Santa Monica for a 3-6 month internship. The role entails focusing on Multi-Modal Gesture Synthesis and involves designing algorithms to create 3D body motion from audio-video input. Responsibilities include full body motion reconstruction, neural rendering using diffusion model-based methods, and managing body animation with 3D body models. The ideal candidate should have prior experience in body-related work, proficiency in 3DMMs and GANs, and at least one publication in the field of full body synthesis. Reporting to supervisors in Applied Science and Research Science departments, the candidate should hold a PhD in Computer Vision or Graphics.
Requirements:
Must be a PhD student specializing in Computer Vision or Graphics.
Ability to process audio-video inputs for predicting 3D body motion.
Conduct full body motion reconstruction in real-world settings.
Proficient in body animation involving 3D body models.
Experienced in utilizing diffusion model-based methods for advanced modeling.
Design algorithms to generate precise outputs from audio-video inputs.
Engage in neural rendering processes to enhance visual results.
Proficiency in body-related work.
Familiarity with 3D Morphable Models (3DMMs) and Generative Adversarial Networks (GANs).
Knowledge working with diffusion models.
Must have at least one publication related to full body synthesis at conferences like ECCV, ICCV, CVPR, or SIGGRAPH.
Salary: $6,000 - $7,000 per month
Flawless promotes an inclusive and safe work environment where individuals can excel. The company is committed to providing equal employment opportunities irrespective of race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. Qualified applicants will be considered regardless of their criminal history, in line with legal regulations.
Flawlessdevstudio
VP of Applied Science
Santa Monica, USA
Santa Monica, USA
Full time
Hybrid
Flawless is at the forefront of innovation in AI filmmaking technology, revolutionizing the industry with its advanced suite of Gen AI film editing tools. Our vision is to equip filmmakers with cutting-edge solutions that foster creativity, expand narrative possibilities, and deliver unparalleled visual and emotional experiences.
Key Responsibilities:
As the Vice President of Applied Science, you will play a pivotal role in a progressive generative AI startup shaping the future of filmmaking. Reporting to the Chief Researcher, you will collaborate closely with Science, VFX, Production, and Product departments. Your primary focus will be on leading the Applied Science teams dedicated to providing advanced production solutions in 3D Vision, Neural Rendering, and Audio Driven Facial Animation. These teams are instrumental in enhancing localization and foreign language adaptation solutions for feature films, episodic series, and commercial content.
The ideal candidate is a forward-thinking, solutions-oriented leader responsible for developing generative AI editing solutions for our global clientele. This role requires exceptional leadership skills to guide scientists and engineers with a deep technical understanding in their respective domains and integration with Product, Engineering, and Production Studio teams. Proficiency in time management, profound knowledge of immersive production trends, and experience in managing multiple high-volume projects on a global scale are crucial. As an Executive Leader, clear and effective communication is essential for successful production. Additionally, this role involves coaching, mentoring, and leading teams and science leaders within the organization. Collaboration with cross-functional teams in both US and UK locations is critical, with direct reporting to the Chief Researcher and close interaction with key production executives, creatives, and Science Leaders.
Qualifications
Over 10 years of leadership experience managing teams of at least 10 Scientists.
More than 15 years of experience in applied/research science or engineering.
Master's degree in Visual Computing, Computer Vision, Computer Graphics, 3D Vision, or a related field, with industry or research experience in deep learning and computer vision.
Proficient in Python/Pytorch, with knowledge of linear algebra, statistical analysis, and numerical optimization.
Experience utilizing cloud platforms like GCP, Azure, or AWS.
Proficiency in generative models for image face synthesis and reconstruction, as well as additional skills in applied research tasks, metric creation, benchmarking, and enhancing solution efficiency.
Extensive experience with CV tools such as OpenCV, scikit, numpy, etc.
Familiarity with differentiable rendering pipelines like PyTorch3D or Taichi Graphics, as well as 3DMM and statistical models.
Proficient in developing machine learning and deep learning approaches, common 2D and 3D Vision tools, and collaboration within research, science, and platform development teams.
Preferred Qualifications
Lead Author and Manager of several published works in reputable CV and Graphics conferences like ICCV, CVPR, Siggraph, NeurIPS.
Experience in developing scalable tools or solutions for multi-modal or audio-driven visual systems in AR/VR or VFX.
Proficiency with C++ or CUDA, knowledge of Transformer, CNN, GAN architectures, and familiarity with Diffusion models and NerFs.
Annual Salary: $250,000 - $300,000
Key Responsibilities:
As the Vice President of Applied Science, you will play a pivotal role in a progressive generative AI startup shaping the future of filmmaking. Reporting to the Chief Researcher, you will collaborate closely with Science, VFX, Production, and Product departments. Your primary focus will be on leading the Applied Science teams dedicated to providing advanced production solutions in 3D Vision, Neural Rendering, and Audio Driven Facial Animation. These teams are instrumental in enhancing localization and foreign language adaptation solutions for feature films, episodic series, and commercial content.
The ideal candidate is a forward-thinking, solutions-oriented leader responsible for developing generative AI editing solutions for our global clientele. This role requires exceptional leadership skills to guide scientists and engineers with a deep technical understanding in their respective domains and integration with Product, Engineering, and Production Studio teams. Proficiency in time management, profound knowledge of immersive production trends, and experience in managing multiple high-volume projects on a global scale are crucial. As an Executive Leader, clear and effective communication is essential for successful production. Additionally, this role involves coaching, mentoring, and leading teams and science leaders within the organization. Collaboration with cross-functional teams in both US and UK locations is critical, with direct reporting to the Chief Researcher and close interaction with key production executives, creatives, and Science Leaders.
Qualifications
Over 10 years of leadership experience managing teams of at least 10 Scientists.
More than 15 years of experience in applied/research science or engineering.
Master's degree in Visual Computing, Computer Vision, Computer Graphics, 3D Vision, or a related field, with industry or research experience in deep learning and computer vision.
Proficient in Python/Pytorch, with knowledge of linear algebra, statistical analysis, and numerical optimization.
Experience utilizing cloud platforms like GCP, Azure, or AWS.
Proficiency in generative models for image face synthesis and reconstruction, as well as additional skills in applied research tasks, metric creation, benchmarking, and enhancing solution efficiency.
Extensive experience with CV tools such as OpenCV, scikit, numpy, etc.
Familiarity with differentiable rendering pipelines like PyTorch3D or Taichi Graphics, as well as 3DMM and statistical models.
Proficient in developing machine learning and deep learning approaches, common 2D and 3D Vision tools, and collaboration within research, science, and platform development teams.
Preferred Qualifications
Lead Author and Manager of several published works in reputable CV and Graphics conferences like ICCV, CVPR, Siggraph, NeurIPS.
Experience in developing scalable tools or solutions for multi-modal or audio-driven visual systems in AR/VR or VFX.
Proficiency with C++ or CUDA, knowledge of Transformer, CNN, GAN architectures, and familiarity with Diffusion models and NerFs.
Annual Salary: $250,000 - $300,000
Flawlessdevstudio
Senior Research Scientist - 3D Vision
Santa Monica, USA
Santa Monica, USA
Full time
Hybrid
Flawless seeks a talented individual as Sr Research Scientist - 3D Vision to join our team. This position offers the opportunity to work at an innovative generative AI startup that is revolutionizing the film industry. Reporting to the Chief Researcher, this role collaborates closely with Science, VFX, Production, and Product teams. The Sr Research Scientist - 3D Vision will lead a group of Research Scientists and Research Engineers in developing solutions related to 3D Vision, Tracking, and Reconstruction for localization and foreign language dubbing within the film industry. Key responsibilities include spearheading the creation of generative AI editing solutions and showcasing leadership in publishing research at respected conferences. Effective time management, strong knowledge of immersive production, and experience managing projects at a global scale are essential. Clear communication and teamwork across different departments in the US and UK are crucial for this position. This role, in consultation with production executives and other key stakeholders, reports to the Chief Researcher.
Qualifications
Minimum Qualifications
Master's degree (PhD preferred) in Visual Computing, Computer Vision, or Computer Graphics, or equivalent work experience in Deep Learning and Visual Computing.
3+ years in a leadership role managing teams of 5+ Scientists/Engineers.
Over 10 years of research experience with a notable publication record in prestigious CV and Graphics conferences.
Demonstrated ability to work collaboratively in a team setting with researchers, data scientists, and developers.
Proven track record of proactive and innovative research.
Strong expertise in linear algebra and statistical analysis.
Hands-on experience with Deep Learning models for virtual avatar reconstruction and animation.
Knowledge of 2D and 3D Vision, Computer Graphics, Deep Learning techniques, and benchmarking methods.
Proficiency in Python and DL frameworks like TensorFlow or PyTorch.
Familiarity with differentiable rendering pipelines such as Mitsuba, PyTorch3D, or Taichi Graphics.
Previous exposure to cloud platforms like AWS, GCP, or Azure.
Preferred Qualifications
Experience developing scalable tools for audio-aware 3D tracking systems and VFX.
Proficiency in C++ or CUDA programming.
Understanding of CNN, Transformer, and GAN architectures.
Knowledge in Diffusion models and Volumetric Neural Rendering.
Qualifications
Minimum Qualifications
Master's degree (PhD preferred) in Visual Computing, Computer Vision, or Computer Graphics, or equivalent work experience in Deep Learning and Visual Computing.
3+ years in a leadership role managing teams of 5+ Scientists/Engineers.
Over 10 years of research experience with a notable publication record in prestigious CV and Graphics conferences.
Demonstrated ability to work collaboratively in a team setting with researchers, data scientists, and developers.
Proven track record of proactive and innovative research.
Strong expertise in linear algebra and statistical analysis.
Hands-on experience with Deep Learning models for virtual avatar reconstruction and animation.
Knowledge of 2D and 3D Vision, Computer Graphics, Deep Learning techniques, and benchmarking methods.
Proficiency in Python and DL frameworks like TensorFlow or PyTorch.
Familiarity with differentiable rendering pipelines such as Mitsuba, PyTorch3D, or Taichi Graphics.
Previous exposure to cloud platforms like AWS, GCP, or Azure.
Preferred Qualifications
Experience developing scalable tools for audio-aware 3D tracking systems and VFX.
Proficiency in C++ or CUDA programming.
Understanding of CNN, Transformer, and GAN architectures.
Knowledge in Diffusion models and Volumetric Neural Rendering.
Flawlessdevstudio
Applied Scientist - Neural Rendering/Compositing
Santa Monica, USA
Santa Monica, USA
Full time
Hybrid
"Flawless, a prominent AI company in Hollywood, is revolutionizing the filmmaking industry with its innovative suite of Gen AI film editing tools. We are dedicated to empowering filmmakers with advanced technology that fosters creativity, expands storytelling capabilities, and delivers exceptional visual and emotional experiences. Flawless is currently seeking an Applied Scientist specializing in Neural Rendering/Compositing. In this role, you will be part of a collaborative and autonomous environment within a growing company at an exciting stage of development. This opportunity allows you to contribute to shaping the future of a caring, creative, and collaborative company.
As an Applied Scientist in Flawless's neural rendering and compositing team, you will collaborate with a passionate team of top-tier researchers addressing complex challenges in Deep Learning, such as multi-modal image synthesis and audio-visual data fusion. Our focus on automated visual translation is just the beginning as we are developing numerous innovative products based on our groundbreaking research. This role offers a remarkable chance to join a team at the forefront of the generative AI revolution.
Minimum Qualifications
MS or Ph.D. in Visual Computing, Computer Vision, or related field
Hands-on experience with neural rendering related to human digitization
3+ years of industry or research experience in deep learning and computer vision, with expertise in Computational Photography (e.g., inpainting, blur, color-space-based modeling, etc.)
Proficiency in domain adaptation techniques for image face synthesis, editing, and restoration
Knowledge of unsupervised, self-supervised, few/zero-shot learning applied to image synthesis/editing/restoration challenges
Familiarity with 3D Computer Vision problems, such as 3D reconstruction & modeling
3+ years of Python experience with competence in deep learning frameworks like PyTorch or Tensorflow
Preferred Qualifications
Proficiency in generative models like GAN and diffusion models, preferably for human synthesis
Expertise in volumetric neural rendering, such as NeRFs and Gaussian Splatting
Experience with differentiable rendering frameworks like Pytorch3D, Mitsuba, etc.
Publications in esteemed venues like Siggraph, Eurographics, ICCV, CVPR, ECCV, etc.
The salary range for this position is $160,000 to $200,000 per year. Flawless is dedicated to creating an equal opportunity and safe working environment where individuals can excel. We are committed to providing fair employment opportunities regardless of race, color, religion, sex, national origin, age, sexual orientation, citizenship, disability, gender identity, or Veteran status. We also consider qualified applicants irrespective of criminal histories, in accordance with legal requirements."
As an Applied Scientist in Flawless's neural rendering and compositing team, you will collaborate with a passionate team of top-tier researchers addressing complex challenges in Deep Learning, such as multi-modal image synthesis and audio-visual data fusion. Our focus on automated visual translation is just the beginning as we are developing numerous innovative products based on our groundbreaking research. This role offers a remarkable chance to join a team at the forefront of the generative AI revolution.
Minimum Qualifications
MS or Ph.D. in Visual Computing, Computer Vision, or related field
Hands-on experience with neural rendering related to human digitization
3+ years of industry or research experience in deep learning and computer vision, with expertise in Computational Photography (e.g., inpainting, blur, color-space-based modeling, etc.)
Proficiency in domain adaptation techniques for image face synthesis, editing, and restoration
Knowledge of unsupervised, self-supervised, few/zero-shot learning applied to image synthesis/editing/restoration challenges
Familiarity with 3D Computer Vision problems, such as 3D reconstruction & modeling
3+ years of Python experience with competence in deep learning frameworks like PyTorch or Tensorflow
Preferred Qualifications
Proficiency in generative models like GAN and diffusion models, preferably for human synthesis
Expertise in volumetric neural rendering, such as NeRFs and Gaussian Splatting
Experience with differentiable rendering frameworks like Pytorch3D, Mitsuba, etc.
Publications in esteemed venues like Siggraph, Eurographics, ICCV, CVPR, ECCV, etc.
The salary range for this position is $160,000 to $200,000 per year. Flawless is dedicated to creating an equal opportunity and safe working environment where individuals can excel. We are committed to providing fair employment opportunities regardless of race, color, religion, sex, national origin, age, sexual orientation, citizenship, disability, gender identity, or Veteran status. We also consider qualified applicants irrespective of criminal histories, in accordance with legal requirements."
Flawlessdevstudio
Research Science Manager
Santa Monica, USA
Santa Monica, USA
Full time
Hybrid
The company is a prominent player in the AI industry based in Hollywood, driving innovation in film editing through cutting-edge Gen AI tools. Their mission is centered on empowering filmmakers with advanced technology that fosters creativity, extends storytelling horizons, and delivers exceptional visual and emotional experiences.
Responsibilities:
The Research Science Manager will directly report to the Chief Researcher, collaborating with Science, VFX, Production, and Product teams. They will oversee the execution of research projects aligned with the Chief Researcher's vision and priorities. This role involves managing project roadmaps for AI teams with a focus on 3D Vision, Neural Rendering Compositing, Audio, and Audio-Driven Facial Animation. The Manager will lead various teams in developing and implementing solutions that impact localization, foreign language dubbing, feature films, episodic series, and commercial content deliveries.
The Research Science Manager will work closely with the Chief Researcher to ensure the successful delivery and Go-To-Market (GTM) strategies across the AI organization. This individual should possess forward-thinking leadership, driving generative AI editing solutions for global clients. Collaboration with Applied Science, Research Science, and Data Performance Engineering teams is key, requiring strong multitasking abilities and effective communication with cross-functional teams across US and UK offices. Deep knowledge of the latest trends in generative AI production, along with proven experience in managing multiple global projects, is essential for this role. Successful collaboration with production executives, creatives, and Science Leaders is critical for successful project delivery.
Requirements
3-5 years of project management experience
3-5 years working within Applied Science and Research Science domains
Completed MS in Visual Computing, Computer Vision, Computer Graphics, 3D Vision, or related field
Previous success in managing at least 2 project roadmaps to market
Proficiency in generative models for image face synthesis and reconstruction
Experience with applied research tasks such as code maintenance, dataset versioning, metric creation, and project roadmap development
Ability to enhance solution efficiency for diversely skilled teams
Experience collaborating in teams consisting of researchers, applied scientists, and platform developers
Preferred Qualifications
Contribution to published work in top-tier CV and Graphics conferences like ICCV, CVPR, Siggraph, NeurIPS
Development of tools or solutions at scale for multi-modal or audio-driven visual systems in AR/VR or VFX
Familiarity with Transformer, CNN, GAN architectures
Proficiency in GAN, CNN, Diffusion models, and NerFs
The salary range for this position is $180,000 - $225,000 per year.
Responsibilities:
The Research Science Manager will directly report to the Chief Researcher, collaborating with Science, VFX, Production, and Product teams. They will oversee the execution of research projects aligned with the Chief Researcher's vision and priorities. This role involves managing project roadmaps for AI teams with a focus on 3D Vision, Neural Rendering Compositing, Audio, and Audio-Driven Facial Animation. The Manager will lead various teams in developing and implementing solutions that impact localization, foreign language dubbing, feature films, episodic series, and commercial content deliveries.
The Research Science Manager will work closely with the Chief Researcher to ensure the successful delivery and Go-To-Market (GTM) strategies across the AI organization. This individual should possess forward-thinking leadership, driving generative AI editing solutions for global clients. Collaboration with Applied Science, Research Science, and Data Performance Engineering teams is key, requiring strong multitasking abilities and effective communication with cross-functional teams across US and UK offices. Deep knowledge of the latest trends in generative AI production, along with proven experience in managing multiple global projects, is essential for this role. Successful collaboration with production executives, creatives, and Science Leaders is critical for successful project delivery.
Requirements
3-5 years of project management experience
3-5 years working within Applied Science and Research Science domains
Completed MS in Visual Computing, Computer Vision, Computer Graphics, 3D Vision, or related field
Previous success in managing at least 2 project roadmaps to market
Proficiency in generative models for image face synthesis and reconstruction
Experience with applied research tasks such as code maintenance, dataset versioning, metric creation, and project roadmap development
Ability to enhance solution efficiency for diversely skilled teams
Experience collaborating in teams consisting of researchers, applied scientists, and platform developers
Preferred Qualifications
Contribution to published work in top-tier CV and Graphics conferences like ICCV, CVPR, Siggraph, NeurIPS
Development of tools or solutions at scale for multi-modal or audio-driven visual systems in AR/VR or VFX
Familiarity with Transformer, CNN, GAN architectures
Proficiency in GAN, CNN, Diffusion models, and NerFs
The salary range for this position is $180,000 - $225,000 per year.
Flawlessdevstudio
Research Scientist - Internship - Innovation
Santa Monica, USA
Santa Monica, USA
Full time
Hybrid
*:
Flawless is a renowned AI company making waves in Hollywood, revolutionizing traditional filmmaking with its innovative Gen AI film editing tools. Our goal is to equip filmmakers with cutting-edge technology that fosters limitless creativity, broadens storytelling horizons, and delivers unparalleled visual and emotional experiences.
Responsibilities:
As a Research Scientist Intern within Flawless’s innovation team, you will collaborate with a dedicated group of top-tier researchers to address complex challenges in generative neural rendering. This includes ventures into audio-driven facial animation, video-based 3D avatar generation, and more. Our exploration in visual dubbing represents just the beginning of our exciting product development pipeline, providing a unique chance to engage with the forefront of the generative technology revolution.
Qualifications:
Currently pursuing a Ph.D. in visual computing, 3D Vision, or related fields.
Strong foundation in mathematics, numerical optimization, and computer graphics.
Proficient in self-directed research with minimal guidance.
Demonstrated research expertise through implementation of methodologies from prestigious conferences in computer vision, graphics, and deep learning.
Familiarity with neural volume rendering, audio-driven facial animation, and 3D tracking techniques.
Proficient in utilizing DL frameworks like PyTorch or TensorFlow, with excellent Python coding skills.
Preferred Qualifications:
Research track record reflected in publications at esteemed conferences in computer vision, graphics, and deep learning (ICCV, CVPR, SIGGRAPH).
Extensive experience in neural volume rendering, audio-driven facial animation, and 3D tracking, especially in areas like 3D face tracking and talking head synthesis from 2D video.
Proficiency in Multi-View, Multi-modal image synthesis and editing.
Hands-on knowledge of NeRF and SDF-based reconstruction techniques.
Understanding of advanced computer graphics techniques such as inverse/differentiable rendering, physics-based rendering, intrinsic image decomposition, and shadow modeling.
Experience with differentiable renderers like PyTorch3D, Mitsuba2, or TensorFlow Graphic.
Salary: $6,200 - $7,000 per month
At Flawless, we prioritize an inclusive environment that fosters equal opportunities for all individuals to excel. We are dedicated to providing equal employment opportunities without bias towards race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. Qualified applicants will be considered regardless of any criminal histories, in compliance with legal regulations.
Flawless is a renowned AI company making waves in Hollywood, revolutionizing traditional filmmaking with its innovative Gen AI film editing tools. Our goal is to equip filmmakers with cutting-edge technology that fosters limitless creativity, broadens storytelling horizons, and delivers unparalleled visual and emotional experiences.
Responsibilities:
As a Research Scientist Intern within Flawless’s innovation team, you will collaborate with a dedicated group of top-tier researchers to address complex challenges in generative neural rendering. This includes ventures into audio-driven facial animation, video-based 3D avatar generation, and more. Our exploration in visual dubbing represents just the beginning of our exciting product development pipeline, providing a unique chance to engage with the forefront of the generative technology revolution.
Qualifications:
Currently pursuing a Ph.D. in visual computing, 3D Vision, or related fields.
Strong foundation in mathematics, numerical optimization, and computer graphics.
Proficient in self-directed research with minimal guidance.
Demonstrated research expertise through implementation of methodologies from prestigious conferences in computer vision, graphics, and deep learning.
Familiarity with neural volume rendering, audio-driven facial animation, and 3D tracking techniques.
Proficient in utilizing DL frameworks like PyTorch or TensorFlow, with excellent Python coding skills.
Preferred Qualifications:
Research track record reflected in publications at esteemed conferences in computer vision, graphics, and deep learning (ICCV, CVPR, SIGGRAPH).
Extensive experience in neural volume rendering, audio-driven facial animation, and 3D tracking, especially in areas like 3D face tracking and talking head synthesis from 2D video.
Proficiency in Multi-View, Multi-modal image synthesis and editing.
Hands-on knowledge of NeRF and SDF-based reconstruction techniques.
Understanding of advanced computer graphics techniques such as inverse/differentiable rendering, physics-based rendering, intrinsic image decomposition, and shadow modeling.
Experience with differentiable renderers like PyTorch3D, Mitsuba2, or TensorFlow Graphic.
Salary: $6,200 - $7,000 per month
At Flawless, we prioritize an inclusive environment that fosters equal opportunities for all individuals to excel. We are dedicated to providing equal employment opportunities without bias towards race, color, ancestry, religion, sex, national origin, sexual orientation, age, citizenship, marital status, disability, gender identity, or Veteran status. Qualified applicants will be considered regardless of any criminal histories, in compliance with legal regulations.