Staff Software Engineer- Search Quality
Databricks6 months ago
Responsibilities
- Own the quality of search and retrieval results for AI agents and human users.
- Optimize hybrid keyword and semantic vector retrieval for precision, recall, intent, and readability.
- Fine-tune ranking models and build relevance scoring and guardrails for grounded AI responses.
- Develop frameworks to measure search quality using human and LLM-based evaluation.
- Improve discovery across heterogeneous enterprise data sources.
Requirements
- Expertise in information retrieval and familiarity with Lucene or Elasticsearch, embeddings, and ranking algorithms.
- Experience or strong interest in building evaluation frameworks using human-in-the-loop and LLM-based methods.
- Deep understanding of relevance metrics including nDCG, MRR, and Precision@K.
- Interest in applying traditional information-retrieval techniques to retrieval-augmented generation.
- Ability to work across structured SQL tables, unstructured documents, and real-time business metrics.
Benefits
- Comprehensive employee benefits and perks, with details varying by region.
Tech Stack
Categories
About Databricks
Databricks is the Data and AI company. More than 20,000 organizations worldwide — including adidas, AT&T, Bayer, Block, Mastercard, Rivian, Unilever, and over 60% of the Fortune 500 — rely on Databricks to build and scale data and AI apps, analytics and agents. Headquartered in San Francisco with 30+ offices around the globe, Databricks offers a unified Data Intelligence Platform that includes Agent Bricks, Lakeflow, Lakehouse, Lakebase and Unity Catalog. --- Databricks applicants Please apply through our official Careers page at databricks.com/company/careers. All official communication from Databricks will come from email addresses ending with @databricks.com or @goodtime.io (our meeting tool).