AI/RAG Engineer — "Full-stack GenAI application engineer"
Looking for someone who has actually shipped a RAG product end-to-end, not just called an LLM API.
- Hands-on with the full RAG pipeline: chunking strategy, embedding model selection, retrieval tuning, reranking, summarization — able to speak to trade-offs at each stage
- Application layer strength: FastAPI, JWT/auth, API Gateway patterns, plus MongoDB/Redis and ideally some Angular/React exposure
- Semantic search and data pipeline experience is called out specifically here — so someone who's built search/retrieval systems (even pre-LLM) transfers well
- This is the most "well-rounded builder" of the three — backend + data pipeline + some frontend awareness
- Good fit: a product-minded backend engineer who's spent the last 1-2 years specifically in applied GenAI/RAG, ideally in a team shipping to real users rather than research/prototyping.