AI Retrieval Engineer

AI Retrieval EngineerRemote — European UnionCompany based in Amsterdam, NetherlandsEnterprise AI | Information Retrieval | RAG | Search Engineering | Generative AI Our client, a growing Enterprise AI company based in Amsterdam, is looking for an AI Retrieval Engineer to build the search and retrieval systems powering production AI applications. You'll work beyond basic RAG implementations, engineering the indexing, search, ranking, and retrieval infrastructure that determines what information reaches LLMs—and how reliably they can use it. What You'll Work On• Build production RAG and retrieval pipelines in Python• Design hybrid search combining semantic and keyword retrieval• Develop search infrastructure using Elasticsearch / OpenSearch• Build and optimise vector retrieval using Qdrant• Design document ingestion, indexing, chunking, and metadata strategies• Develop ranking and reranking pipelines• Improve retrieval relevance, precision, latency, and scalability• Build evaluation frameworks to measure retrieval quality• Integrate retrieval services with LLM APIs and enterprise AI applications• Work with PostgreSQL and structured data alongside unstructured knowledge sources• Monitor and optimise retrieval performance in production Core Skills• 3+ years in Search Engineering, AI Engineering, ML Engineering, Backend Engineering, or similar roles• Python• RAG architectures• Elasticsearch and/or OpenSearch• Vector databases such as Qdrant• PostgreSQL• LLM APIs• Strong understanding of information retrieval and production search systems Nice to HaveBM25 and dense retrievalHybrid and semantic searchCross-encoder / LLM rerankingEmbedding modelspgvectorPinecone / WeaviateLangChain / LangGraph / LlamaIndexRetrieval evaluation frameworksDocument parsing and ingestion pipelinesMulti-tenant enterprise searchKubernetes / Docker / cloud infrastructure