Lead horizontal metric and evaluation frameworks that quantify engagement, productivity gains, and end-to-end system quality across GenAI models, agentic tooling, context grounding, and safety. Deliver clear, executive-ready insights and recommendations that guide product roadmaps, organizational transitions, and resource allocation. Work on challenges across behavioral, telemetry, and evaluation datasets to identify user adoption, quality or reliability gaps, latency/cost trade-offs, and new methodologies to improve performance.
Define upstream logging and telemetry standards, design scalable data models and ETL pipelines, and build unified semantic layers and self-serve analytics that connect data across Workspace domains. Drive experimentation, observational causal inference, and rigorous model evaluations—leveraging AI models/tools as well as human and automated rating systems.
Job description provided by Google.
View the original posting
