Machine Learning Staff Software Engineer, Search Personalization

Google Google · Big Tech · Mountain View, CA +1

Staff ML Engineer for Google Search Personalization, focusing on building and scaling foundational user models for retrieval and ranking. This role involves designing and implementing personalized user models, including Neural Deep Retrieval, LLM-based RAG, and clustering models, to power user engagement and content discovery across various modalities and use cases. The position requires significant experience in ML design, deployment, and scaling of recommendation systems in production.

What you'd actually do

  1. Design and implement personalized user models to optimize for user happiness, including Neural Deep Retrieval Models, Deep Neural Network Ranking/Scoring models, User/Content Clustering Models, Large Language Models (LLM)-based Retrieval Augmented Generation Models, and more.
  2. Build user and content clustering models to enable core personalization and ranking use cases.
  3. Enhance model performance and personalization precision/recall through advanced modeling techniques such as transformers, distillation, reward shaping, multi-task learning, neural bandits, etc. and capabilities through feature engineering, automatic parameter tuning, label quality engineering, etc.
  4. Scale the model's applications to a multitude of modalities (content, queries, videos and notifications) and use cases (retrieval, ranking, content generation, diversification, etc.).
  5. Create next-generation realtime ML models that can capture new user interests and world trends in seconds and scale model training and serving to billions of users.

Skills

Required

  • software development
  • building and deploying recommendation systems models
  • ML design
  • ML infrastructure
  • model deployment
  • model evaluation
  • data processing
  • debugging
  • fine tuning
  • testing software products
  • launching software products
  • software design
  • software architecture

Nice to have

  • data structures
  • algorithms
  • recommender systems
  • clustering algorithms
  • SQL
  • deep model
  • C++
  • Dremel/F1
  • TensorFlow
  • research

What the JD emphasized

  • building foundational user models
  • powering Discover’s retrieval and ranking
  • Neural Deep Retrieval
  • Activity Clustering
  • Reinforcement Learning
  • Multi-Objective Ranking
  • LLM-based Retrieval Augmented Generation Models
  • realtime ML models
  • scale model training and serving to billions of users
  • building and deploying recommendation systems models
  • ML design and ML infrastructure
  • launching software products

Other signals

  • building foundational user models
  • powering Discover’s retrieval and ranking
  • Neural Deep Retrieval
  • Activity Clustering
  • Reinforcement Learning
  • Multi-Objective Ranking
  • LLM-based Retrieval Augmented Generation Models
  • realtime ML models
  • scale model training and serving to billions of users