Cheikh S.

I build production AI systems that ship: RAG apps, LLM backends, Agentic platforms. For the last 10+ years I have built software. For the last few years the work has been AI engineering: retrieval-augmented generation, LLM integrations, and the FastAPI services behind them. Recent work includes an AI backend for a major media company (FastAPI, LangChain, RAG with vector search, Cloud Run, OAuth) and senior platform engineering before that. What I take on: - RAG and LLM applications: document Q&A, internal copilots, structured extraction - AI backends: FastAPI, LangChain, queues, evals, and CI so the model layer does not fall over in production - Full-stack product work when the AI feature needs a real app: React, Django, PostgreSQL Stack I use in production, not just in demos: Python, FastAPI, LangChain, PostgreSQL, Docker, GCP, AWS, React. I work directly with founders and product teams. You get a working system, not a notebook. Message me with the workflow you want automated and I will tell you if RAG, a simpler API integration, or no AI at all is the right call.