We’re working with a fast-growing AI company looking for a Senior Retrieval / RAG Engineer to take ownership of the retrieval layer at the heart of its production AI platform. You’ll own everything from document ingestion, chunking and embeddings through to hybrid search, reranking, evaluation and agentic retrieval. This is a highly hands-on role where you’ll have real influence over architecture and technical direction, building AI systems that need to retrieve the right information accurately and reliably at scale. Fully remote anywhere within the EU.
Must Haves
5+ years of production backend engineering experience
2+ years building and operating RAG / retrieval systems in production
Strong Python experience
FastAPI or similar production Python frameworks
Production experience with vector databases such as Qdrant, Pinecone, Weaviate or similar
Strong understanding of embeddings, semantic search, hybrid retrieval and reranking
Experience evaluating retrieval quality using metrics such as Recall@K and NDCG
PostgreSQL / SQL
Experience diagnosing and improving retrieval performance in production
Comfortable taking genuine end-to-end ownership
Nice to Haves
Agentic retrieval and multi-step search workflows
Query decomposition
BM25 / information retrieval experience
Golden datasets and retrieval regression testing
Large-scale or OCR-heavy document ingestion
Redis and background processing
Multi-tenant architectures and data isolation
Multilingual retrieval/search
Experience benchmarking different embedding models, vector databases or LLM approaches
Experience using AI coding tools such as Claude Code, Copilot or similar