Databricks

4 months ago

Staff Software Engineer- Search Quality

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 5 hours agoStatus: Live

Job Summary

As a Staff Software Engineer - Search Quality, you own the quality of search results powering both AI agents and human users. You’ll optimize the retrieval layer, balance hybrid keyword and semantic search, and build evaluation frameworks to measure relevance. You will work on ranking models, data heterogeneity, and guardrails to keep AI grounded, impacting thousands of users relying on fast, accurate search across structured and unstructured data.

Location: Bengaluru

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Key Responsibilities

•Own the quality of search results for AI agents and human users, ensuring accurate, high-recall results across data sources.
•Balance traditional keyword-based search with semantic vector search to support hybrid retrieval.
•Develop and maintain guardrails and relevance scoring to prevent hallucinations and keep outputs grounded in data.
•Design and implement evaluation frameworks (human-in-the-loop and LLM-based) to measure relevance using metrics like nDCG, MRR, and Precision@K.
•Collaborate with data scientists and engineers to integrate retrieval across structured SQL data, unstructured documents, and real-time metrics.

Key Requirements

•Experience with Lucene/Elasticsearch, embeddings, and ranking algorithms.
•Ability to build evaluation frameworks for relevance using human-in-the-loop and LLm-based methods (nDCG, MRR, Precision@K).
•Experience applying IR knowledge to Retrieval-Augmented Generation (RAG).
•Strong understanding of information retrieval across structured SQL, unstructured docs, and real-time metrics.
•Strong communication and collaboration in cross-functional teams.

Experience:Information retrievalIRSearch qualitySemantic searchRAG

Skills:LuceneElasticsearchEmbeddingsRanking algorithmsNDCGMRRPrecision@KRetrieval-Augmented GenerationRAGInformation retrievalLLMsHybrid retrieval

Languages:English

Tech Stack:LuceneElasticsearchEmbeddingsRanking algorithmsNDCGMRRPrecision@KRAGLLMsSemantic searchKeyword search

Company Brief

Databricks

Provides a unified data analytics platform powered by Apache Spark to simplify building, deploying, and scaling data engineering, data science, and machine learning workloads for enterprises.

Industry: Data Infrastructure

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series E+

Headquarters: San Francisco, United States

Founded: 2013

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Databricks

4 months ago

Staff Software Engineer- Search Quality

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 5 hours agoStatus: Live

Job Summary

Location: Bengaluru

Workplace: Onsite

Employment Type: Full time

Job Function: Software Engineering

Key Responsibilities

•Own the quality of search results for AI agents and human users, ensuring accurate, high-recall results across data sources.
•Balance traditional keyword-based search with semantic vector search to support hybrid retrieval.
•Develop and maintain guardrails and relevance scoring to prevent hallucinations and keep outputs grounded in data.
•Design and implement evaluation frameworks (human-in-the-loop and LLM-based) to measure relevance using metrics like nDCG, MRR, and Precision@K.
•Collaborate with data scientists and engineers to integrate retrieval across structured SQL data, unstructured documents, and real-time metrics.

Key Requirements

•Experience with Lucene/Elasticsearch, embeddings, and ranking algorithms.
•Ability to build evaluation frameworks for relevance using human-in-the-loop and LLm-based methods (nDCG, MRR, Precision@K).
•Experience applying IR knowledge to Retrieval-Augmented Generation (RAG).
•Strong understanding of information retrieval across structured SQL, unstructured docs, and real-time metrics.
•Strong communication and collaboration in cross-functional teams.

Experience:Information retrievalIRSearch qualitySemantic searchRAG

Skills:LuceneElasticsearchEmbeddingsRanking algorithmsNDCGMRRPrecision@KRetrieval-Augmented GenerationRAGInformation retrievalLLMsHybrid retrieval

Languages:English

Tech Stack:LuceneElasticsearchEmbeddingsRanking algorithmsNDCGMRRPrecision@KRAGLLMsSemantic searchKeyword search

Company Brief

Databricks

Provides a unified data analytics platform powered by Apache Spark to simplify building, deploying, and scaling data engineering, data science, and machine learning workloads for enterprises.

Industry: Data Infrastructure

Company Size: Enterprise (1,001+ employees)

Revenue: USD 1B+

Growth: Scaleup

Valuation: Unicorn (USD 1B+)

Funding: Series E+

Headquarters: San Francisco, United States

Founded: 2013

Website LinkedIn