Senior Staff Applied AI Engineer - Context Retrieval

Databricks is hiring a Senior Staff Applied AI Engineer to own context retrieval for Databricks agents across SaaS providers. This is a zero-to-one role with two charters: build the retrieval stack (query understanding, content understanding, ranking, retrieval, evaluation) across enterprise SaaS data, and build search subagents that reason about what context is needed and whether the right thing came back.

• Build the full retrieval stack from scratch: query understanding, content understanding and indexing, hybrid retrieval, ranking, and evaluation.
• Retrieve across heterogeneous data: structured assets (tables, columns, SQL queries, dashboards, code, notebooks, jobs) and unstructured content (docs, wikis, tickets, chat, images, video, audio).
• Connect to SaaS surface areas customers use, building connectors and retrieval adapters with freshness, permissions, and ranking signals.
• Optimize retrieval for both LLMs (grounded, token-efficient, hallucination-resistant) and humans (intuitive, explainable discovery).
• Crack query understanding for agents: query rewriting, decomposition, intent classification, entity resolution for multi-turn agentic workflows.
• Build pipelines for content understanding at scale: structure, entities, embeddings, summaries, metadata.
• Design search subagents that plan multi-hop searches, issue follow-up queries, ground claims, and signal failure.
• Build evaluation flywheel: offline evals (nDCG, MRR, Recall@K, Precision@K), LLM-as-judge, human-in-the-loop labeling, online experimentation.
• Set technical direction, mentor senior engineers, partner with Research, Product, and Platform leaders.

• 10+ years of software engineering experience, with significant time building production retrieval, search, or RAG systems at scale.
• Deep Information Retrieval expertise: lexical retrieval (BM25, Lucene/Elasticsearch/OpenSearch), dense retrieval (embeddings, ANN indexes — FAISS, ScaNN, HNSW), hybrid retrieval, learning-to-rank.
• Hands-on experience with LLM-era retrieval: RAG architectures, query rewriting, re-ranking with cross-encoders, long-context strategies, grounding techniques.
• Experience designing agentic systems on top of retrieval: search planners, multi-hop/iterative retrieval, self-reflection, tool-using agents.
• Strong grasp of relevance evaluation: nDCG, MRR, Precision@K, Recall@K; offline/online experimentation; LLM-as-judge frameworks.
• Experience across structured and unstructured data.
• Track record of building 0→1 systems.
• Demonstrated technical leadership.

• Experience building retrieval over enterprise SaaS sources (permissions, freshness, multi-tenancy, ACL-aware indexing).
• Background in agentic systems, tool use, or multi-turn retrieval for LLM agents.
• Contributions to open-source IR/search projects or publications at SIGIR, KDD, WWW, EMNLP.
• Experience training or fine-tuning embedding models, rerankers, or query understanding models.

Local Pay Range: $228,600—$342,800 USD. Total compensation may include annual performance bonus, equity, and benefits. Databricks offers comprehensive benefits and perks; details vary by region.

This role is based in Mountain View, CA or San Francisco, CA office. Hybrid in-office collaboration expected.

Apply via the provided job link.