Build a unified retrieval layer across enterprise systems
Design hybrid retrieval pipelines combining lexical, dense, and structured methods
Engineer ingestion and freshness pipelines for millions of documents
Own permission-aware retrieval mirroring ACLs across sources
Build query understanding for agents: intent parsing and entity linking
Design chunking and embedding strategies for varied content

🎯 Requirements

3-5 years building production search or knowledge-base systems
Proficiency in Python, Go, Java, or similar
Experience with OpenSearch/Elasticsearch/Solr/Vespa and index design
Strong IR fundamentals: TF-IDF, BM25, learning-to-rank
Experience with vector search and embeddings: FAISS, Pinecone, Weaviate, Milvus
Familiarity with RAG pipelines and semantic search in production

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot