AI/LLM Engineer — Backend & API Integration
We are looking for an experienced AI/LLM Backend Engineer to join an existing mobile application project currently in active development. The application and core product architecture are already being developed by our existing team. We are looking for a dedicated AI specialist who will be responsible for the AI/LLM integration layer and supporting backend architecture. This is not a general mobile development position and not a prompt-writing role.
What We Need
We need someone who understands how to build a reliable production layer between a mobile application, backend systems and external AI/LLM services. The initial architecture should be API-based, practical and cost-efficient for an MVP, without requiring us to train or host our own large model. The system should also be designed so it can evolve later without rebuilding the entire AI architecture.
Responsibilities
* Design and implement the AI/LLM backend integration layer
* Integrate external LLM APIs
* Build secure server-side communication with AI providers
* Implement structured AI inputs and outputs
* Implement tool/function calling where required
* Design conversational context and memory
* Validate and process AI responses before they reach application logic
* Implement retries, timeouts, error handling and fallback behaviour
* Protect API credentials and sensitive backend logic
* Implement logging, monitoring and usage controls
* Optimize token usage, latency and API costs
* Design the system for future scaling and additional AI providers
* Work closely with our existing developer and integrate into the current application architecture
Who We Are Looking For
The ideal candidate has real experience building production AI/LLM systems, not only experimenting with prompts or connecting a basic chatbot API.
Strong experience with:
* Python and backend development
* LLM API integrations
* OpenAI or comparable AI platforms
* Structured outputs / JSON schemas
* Tool / function calling
* Conversational AI and context management
* API and backend security
* Databases and caching
* Docker / cloud environments
* Error handling and fallback architecture
* AI cost and latency optimization
Experience with MCP, multiple LLM providers, AI evaluation, open-source models or self-hosted inference is a strong advantage.
Project Structure
You will work alongside an existing developer rather than replacing the current development team. The first goal is to build a lean and reliable MVP AI architecture using external AI services, while keeping the system flexible enough for future expansion. Detailed product architecture, documentation and internal logic will only be shared with shortlisted candidates. Shortlisted specialists may be offered a small paid technical evaluation before the main work begins. Budget: $1,500 for the initial scope, depending on experience and proposed architecture.
Potential for long-term collaboration.
