Backend Engineer — AI Integrations & RAG

We build AI systems that ship — support agents, RAG search, fraud scoring, computer vision, voice — for fintech, e-commerce and retail clients. RAG is the core of a lot of that, and we need someone who actually owns it: not just wiring an API call to an LLM, but deciding how chunking, retrieval and ranking should work for a given dataset, and being able to explain why.

This is a hands-on role. You'll be building the backend these systems run on, integrating LLM APIs into real production traffic, and making the calls that decide whether retrieval quality is actually good or just looks good in a demo.

• Design and implement RAG pipelines end-to-end: chunking, embeddings, retrieval, ranking, evaluation
• Integrate LLM APIs (OpenAI, Anthropic, and others) into production backend services
• Own architecture decisions for AI features — what actually improves retrieval quality, not just what's easiest to wire up
• Work with real client data and production traffic, not toy datasets or demos
• Build and maintain the Python backend these systems run on

• Real hands-on experience building RAG systems — you can talk specifics about chunking strategy, embeddings, retrieval, not just "I called the OpenAI API once"
• Strong Python — this is a Python shop, you'll be reviewed and paired with in Python
• Experience integrating LLM APIs into a real backend, in production, not a notebook
• Comfortable with vector databases and semantic search infrastructure
• Solid backend fundamentals: APIs, databases, production reliability

• Experience with Django specifically
• Familiarity with evaluating retrieval/RAG quality, not just eyeballing results
• Experience with agentic or tool-calling LLM pipelines

• Remote-first
• Real production work — code that ships to real users
• Flexible hours, results over facetime