Evaluate and model launch analysis. Work cross-functionally on data collection, management, quality measurement and improvements. Improve end-to-end evaluations by incorporating user and product feedback, and providing continuous production evaluation/verification for model releases. Provide user feedback analysis and insights to improve our frontier models and the user experiences. Solve complex, high-impact research and engineering challenges where the solution is non-obvious to executive leaders.
Job description provided by Google.
View the original posting