Help to establish metrics, benchmarking Generative-AI issues and quantify improvements. Develop datasets and run evals for engineers to evaluate and improve Search, Labs and Assistant products. This role works with sensitive content and may be exposed to graphic, controversial, or upsetting content. Use technical judgment to drive project delivery, challenge proposals and identify risks. Manage interdependent projects of moderate to high complexity against crashed timelines.
Improve tools through data analysis, technical expertise, and presentations to key stakeholders. Enhance operational workflows via process improvements and identification of automation opportunities. Design, develop, and scale production-grade LLM-as-a-judge autoraters and automated evaluation systems to run real-time launch decisions and continuous regression testing across core verticals. Partner directly with Product, Search Core, and GDM engineering teams to drive alignment on technical roadmaps, integrations and cross-product risk registers.
Job description provided by Google.
View the original posting
