Senior Staff Applied AI Engineer - Context Retrieval

The Mission

Databricks agents are only as good as the context they can retrieve. Whether an agent is answering a question about last quarter's revenue, debugging a failing job, generating SQL against a 10,000-table lakehouse, or summarizing a Wiki page, its quality is bounded by what it can find — and how well it understands what it finds.

We are 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 deeply connected charters:

• Build the retrieval stack — query understanding, content understanding, ranking, retrieval, and evaluation — across Enterprise SaaS data stored across multiple systems.
• Build the search subagents that sit on top of that stack and reason about what context is needed, how to retrieve it, and whether the right thing actually came back.

What You Will Do

• Build the full retrieval stack from scratch: Own the end-to-end system including query understanding, content understanding and indexing, hybrid retrieval, ranking, and evaluation.
• Retrieve across heterogeneous data — structured and unstructured: Index and rank across structured assets (tables, columns, SQL queries, dashboards, code, notebooks, jobs) and unstructured content (docs, wikis, tickets, chat, images, video, audio).
• Connect to the SaaS surface area customers use: Build connectors and retrieval adapters for systems where enterprise knowledge lives, treating each retrieval source with its own freshness, permissions, and ranking signals.
• Optimize for both LLMs (grounded, token-efficient, hallucination-resistant context) and humans (intuitive, explainable discovery).
• Build query understanding for multi-turn agentic workflows: query rewriting, decomposition, intent classification, and entity resolution.
• Build pipelines that extract structure, entities, embeddings, summaries, and metadata across asset types.
• Build search subagents that reason about retrieval: Design the agentic layer that plans multi-hop searches, issues follow-up queries, grounds claims against retrieved evidence, and hands back high-confidence context.
• Build evaluation flywheels: Stand up offline evals (nDCG, MRR, Recall@K, Precision@K), LLM-as-judge harnesses, human-in-the-loop labeling, and online experimentation.
• Set technical direction, multi-year roadmap, mentor senior engineers, and raise the technical bar across the org.

What We're Looking For

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

Nice to Have

• 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 venues like SIGIR, KDD, WWW, or EMNLP.
• Experience training or fine-tuning embedding models, rerankers, or query understanding models.