Lead a team of engineers, driving career growth, team culture, and execution across data collection, evaluation generation, and unified benchmarks. Act as Tech Lead for the Quality Flywheel, architecting systems for scalable data collection, realistic simulation environments, eval generation, and online hill climbing. Direct software design and implementation for next-gen evaluation infrastructure (Eval Infra), tooling, and Gemini post-training systems adhering to architectural best practices.
Partner across teams to distill complex, ambiguous model and platform requirements into simplified, robust technical solutions. Drive overarching testing and reliability architecture, advocating production stability, test environment improvements, and on-call operational support.
Job description provided by Google.
View the original posting
