Senior Research Scientist - 3D Vision
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.