Applied Scientist, Vertical Search

Amazon Amazon · Big Tech · IN, KA, Bengaluru · Applied Science

This role focuses on building and improving machine learning models for Amazon's vertical search, specifically developing new ranking features and techniques. The scientist will be responsible for the full development cycle, from design and implementation to A/B testing and production deployment, aiming to enhance search quality and effectiveness across Amazon's product ecosystem.

What you'd actually do

  1. Build machine learning models for Product Search.
  2. Develop new ranking features and techniques building upon the latest results from the academic research community.
  3. Propose and validate hypothesis to direct our business and product road map. Work with engineers to make low latency model predictions and scale the throughput of the system.
  4. Design, develop, and implement production level code that serves billions of search requests. Own the full development cycle: design, development, impact assessment, A/B testing (including interpretation of results) and production deployment.
  5. Take ownership. Understand the needs of various search teams, distill those into coherent projects, and implement them with an eye on long-term impact.

Skills

Required

  • Experience programming in Java, C++, Python or related language
  • Experience with SQL and an RDBMS (e.g., Oracle) or Data Warehouse

Nice to have

  • Experience implementing algorithms using both toolkits and self-developed code
  • Have publications at top-tier peer-reviewed conferences or journals

What the JD emphasized

  • production level code
  • low latency model predictions
  • scale the throughput of the system
  • billions of search requests
  • impact assessment
  • A/B testing
  • production deployment

Other signals

  • develops sophisticated search solutions
  • build next-generation search infrastructure
  • invent universally applicable signals and algorithms for training machine-learned ranking models
  • improve the machine-learning framework for training and offline evaluation