Staff Software Engineer - Search Quality
Databricks is a data and AI platform that lets organizations build analytics, AI agents, and applications on a unified, governed lakehouse.
Maintainer signals as of 9/25/2026
Funding history
Investors
About Databricks
Data engineers, analysts, and AI teams use Databricks to process large datasets, build reliable pipelines, and train models on a single governed platform. Users can run SQL analytics, serve ML predictions in real time, and deploy AI agents grounded in enterprise data. Its open lakehouse architecture provides consistent security and governance across analytical and operational workloads.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will own search-result quality for AI agents and human users. You will optimize retrieval, improve search interfaces, balance keyword and semantic vector search, tune ranking models, build relevance guardrails and evaluation frameworks, and connect structured, unstructured, and real-time data sources.
Requirements
- Knowledge of Lucene or Elasticsearch, embeddings, and ranking algorithms
- Experience building human-in-the-loop and LLM-based evaluation frameworks
- Knowledge of relevance metrics, including nDCG, MRR, and Precision@K
- Knowledge of information retrieval and retrieval-augmented generation
Responsibilities
- Own search-result quality for AI agents and human users
- Optimize retrieval for LLM reasoning over data
- Improve search experiences for finding assets and answers
- Balance keyword search with semantic vector search
- Fine-tune ranking models for human readability and LLM-ready context
- Build relevance guardrails and scoring to improve AI accuracy
- Connect structured SQL tables, unstructured documents, and real-time business metrics