Senior RAG Engineer

We’re working with a fast-growing AI company building sophisticated, production-grade AI products used to work with large volumes of complex and confidential information. They’re looking for a Senior Retrieval / RAG Engineer to take ownership of the retrieval layer at the heart of their AI platform. This is a genuinely hands-on role covering everything from document ingestion and embeddings through to hybrid search, reranking, evaluation and agentic retrieval. You’ll have significant technical ownership and the freedom to influence architecture and engineering decisions as the company scales. What you'll be working onBuilding and owning production RAG / retrieval pipelinesDocument parsing, chunking, embeddings and indexingSemantic + keyword/hybrid searchVector databases and search optimisationRanking, reranking and retrieval qualityAgentic retrieval, query decomposition and multi-step searchGolden datasets, regression testing and retrieval evaluationLarge-scale document ingestion and background processingBuilding scalable backend services with Python & FastAPIMulti-tenant architecture, security and data isolation What we're looking for5+ years of production backend engineering experience, including 2+ years building production retrieval/RAG systems. Strong experience with:PythonFastAPI or similarVector databases such as Qdrant, Pinecone, Weaviate, Milvus or similarEmbeddings & semantic searchHybrid retrieval & rerankingPostgreSQL / SQLRetrieval metrics such as Recall@K, NDCG and BM25 We're particularly interested in engineers who have operated retrieval systems in production, diagnosed retrieval problems and can demonstrate improvements through data rather than simply testing a handful of prompts. The environmentThis is a fast-moving, high-growth AI company where you'll have genuine ownership. You'll be expected to make architectural decisions, experiment with new approaches and take responsibility for what you put into production.