Software Engineer, Workspace Search Quality

Google Google · Big Tech · Bengaluru, Karnataka, India

Software Engineer role focused on improving search quality within Google Workspace by developing and deploying ML models, enhancing search relevance, and establishing evaluation frameworks. The role involves integrating advanced ML technologies, LLMs, RAG, and agentic architectures to create intuitive searching and finding experiences across Workspace products.

What you'd actually do

  1. Lead the architecture, design and implementation of end-to-end search solutions, from understanding natural language queries to developing and deploying machine learning models that significantly improve search quality.
  2. Drive innovation by exploring and integrating machine learning techniques, algorithms, and architectures to enhance search relevance and user experience.
  3. Own the technical goal and roadmap for critical areas of Workspace Search, collaborating with cross-functional teams to define and deliver on a strategic roadmap.
  4. Establish and refine evaluation frameworks and metrics to measure and track progress against key performance-indicators.

Skills

Required

  • Information Retrieval (IR)
  • Natural Language Processing (NLP)
  • Machine Learning (ML)
  • large-scale system design
  • distributed systems
  • production quality systems

Nice to have

  • embedding-based retrieval
  • vector search
  • query understanding
  • Large Language Models (LLMs)
  • search/recommendation systems
  • system latency improvements
  • scalability enhancements
  • defining metrics
  • analyzing user-perception surveys
  • complex search experiments
  • agentic architectures
  • tool-calling
  • Retrieval-Augmented Generation (RAG)

What the JD emphasized

  • 8 years of experience in software engineering with Information Retrieval (IR), Natural Language Processing (NLP) or Machine Learning (ML)
  • Experience with launching user-facing, large-scale, production quality systems
  • Experience designing, implementing, and optimizing large-scale, high-performance, distributed search or quality systems in production environments

Other signals

  • integrating machine learning techniques
  • deploying machine learning models
  • advanced Machine Learning (ML) technologies
  • embedding-based retrieval
  • vector search
  • Large Language Models (LLMs) applied to search/recommendation systems
  • agentic architectures
  • tool-calling
  • Retrieval-Augmented Generation (RAG)