Job Description

Role summary
We're looking for a Python Developer to build and scale AI-powered backend services that automate workflows, analyse emails/documents, and deliver secure, permission-based Q&A and reporting. You'll work on production-grade APIs, data pipelines, and retrieval systems (RAG/GraphRAG) in a privacy-first environment (on-prem / customer-controlled).
Responsibilities
Build and maintain FastAPI services (REST endpoints, auth, background jobs, rate limiting).
Implement RAG / GraphRAG pipelines: chunking, embeddings, retrieval, re-ranking, citations, evaluation.
Integrate and operate databases like ElasticSearch/FAISS/Vector DB for semantic search.
Implement permissions & governance (role-based access, audit logs, data boundaries across departments).
Integrate with LLMs (local inference via Ollama / APIs when needed), prompt orchestration, tool calling.
Write tests, improve performance, monitor services, and support deployments (Docker/Linux).
Collaborate ...

Ready to Apply?

Take the next step in your AI career. Submit your application to RaceMyDesk today.

Submit Application