Databricks

4 months ago

Senior 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: 2 hours agoStatus: Live

Job Summary

Seeking a Senior Staff Software Engineer to lead search quality for Databricks' retrieval backbone. You will own result quality for AI agents and human users, optimize hybrid retrieval and ranking, and build evaluation frameworks to measure relevance (nDCG, MR R, Precision@K) across structured and unstructured data. You’ll work on semantic vector search, guardrails for accuracy, and Retrieval-Augmented Generation in a high-impact data/AI environment.

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 and actionable insights across data sources.
•Develop and tune hybrid retrieval systems balancing keyword-based search with semantic vector search for intent and recall.
•Design and implement ranking models and evaluation frameworks (human-in-the-loop and LLM-based) to measure relevance metrics.
•Build guardrails and scoring mechanisms to prevent hallucinations and ensure ground-truth grounding for AI actions.
•Address data heterogeneity by integrating signals from structured SQL, unstructured docs, and real-time metrics.

Key Requirements

•The IR Specialist: You know your way around Lucene/Elasticsearch, embeddings, and ranking algorithms.
•The Quality and Metrics Obsessive: You understand that "relevance" is subjective and love building evaluation frameworks (human-in-the-loop and LLM-based) to measure it. You are obsessed with relevance metrics (nDCG, MRR, Precision@K).
•The Bridge Builder: You’re excited to apply traditional Information Retrieval (IR) wisdom to the cutting-edge world of Retrieval-Augmented Generation (RAG).
•Experience with hybrid retrieval (keyword-based search and semantic vector search) and dual-optimization of ranking models.
•Hands-on experience in building guardrails and relevance scoring to keep AI outputs grounded in reality.

Experience:DataAISearchInformation retrievalRAG

Languages:English

Tech Stack:LuceneElasticsearchEmbeddingsRanking algorithmsNDCGMRRPrecision@KRAGSemantic searchHybrid retrieval

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

Senior 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: 2 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 and actionable insights across data sources.
•Develop and tune hybrid retrieval systems balancing keyword-based search with semantic vector search for intent and recall.
•Design and implement ranking models and evaluation frameworks (human-in-the-loop and LLM-based) to measure relevance metrics.
•Build guardrails and scoring mechanisms to prevent hallucinations and ensure ground-truth grounding for AI actions.
•Address data heterogeneity by integrating signals from structured SQL, unstructured docs, and real-time metrics.

Key Requirements

•The IR Specialist: You know your way around Lucene/Elasticsearch, embeddings, and ranking algorithms.
•The Quality and Metrics Obsessive: You understand that "relevance" is subjective and love building evaluation frameworks (human-in-the-loop and LLM-based) to measure it. You are obsessed with relevance metrics (nDCG, MRR, Precision@K).
•The Bridge Builder: You’re excited to apply traditional Information Retrieval (IR) wisdom to the cutting-edge world of Retrieval-Augmented Generation (RAG).
•Experience with hybrid retrieval (keyword-based search and semantic vector search) and dual-optimization of ranking models.
•Hands-on experience in building guardrails and relevance scoring to keep AI outputs grounded in reality.

Experience:DataAISearchInformation retrievalRAG

Languages:English

Tech Stack:LuceneElasticsearchEmbeddingsRanking algorithmsNDCGMRRPrecision@KRAGSemantic searchHybrid retrieval

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