You will lead the team that owns Discover's interpretable, token-based user models, including Long-Term Interest and Creator models. These are the models that build the billions of interest profiles above, and the ones other Google products rely on.
In Google Search, we're reimagining what it means to search for information – any way and anywhere. To do that, we need to solve complex engineering challenges and expand our infrastructure, while maintaining a universally accessible and useful experience that people around the world rely on. In joining the Search team, you'll have an opportunity to make an impact on billions of people globally. Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
US: $207000 - $300000 (USD) + 20% bonus target + equity + benefits
Learn more about benefits at Google.
Manage and grow a team of engineers, mixing senior technical leads and early-career engineers, while developing each engineer's career and building a high-velocity team culture.
Partner closely with DeepMind and Infra teams, and own our models end-to-end, from research ideas to production launches, at a scale few places can offer.
Set and own the multi-quarter technical strategy and roadmap for token-based user modeling with the team's tech leads, product management, and partner teams.
Drive the rebuild of interest-vocabulary redesign, unification of the token models, and the next-generation model architecture by making sound technical trade-offs and running thorough design reviews.
Raise the bar on experimentation and evaluation by investing in offline evaluation that predicts online results (including LLM-based autoraters), faster iteration loops, and disciplined live-experiment and launch practices.
Minimum qualifications
Bachelor’s degree or equivalent practical experience.
8 years of experience in software development, including 5 years in machine learning, recommendation, personalization, ads or search quality.
2 years of experience in a people management or team leadership role.
Experience training, evaluating, or launching models for recommender systems.
Experience with applied machine learning for recommendation, retrieval, or search platforms.
Preferred qualifications
Experience re-architecting production ML systems while maintaining downstream compatibility and stability.
Management experience, leading a team of 5 or more engineers.
Knowledge of modern recommender-system and ML techniques (e.g., user modeling, embedding-based and two-tower retrieval, sequence models and Transformers, distillation, multi-task and multi-objective learning, and applying LLMs to recommendation).
A track record of leading ML projects from design to launch that require coordinating multiple teams.
Excellent written and verbal communication, and the ability to align stakeholders with different priorities.
Bachelor’s degree or equivalent practical experience.
8 years of experience in software development, including 5 years in machine learning, recommendation, personalization, ads or search quality.
2 years of experience in a people management or team leadership role.
Experience training, evaluating, or launching models for recommender systems.
Experience with applied machine learning for recommendation, retrieval, or search platforms.
