Lead Protege's DataLab research organization, defining strategy for AI training data quality, evaluation systems, and marketplace optimization while managing researchers and partnering with Product, Engineering, and GTM.
Lead the design and validation of trustworthy benchmarks and evaluations for frontier AI models, including agentic and domain-specific tasks. Own the science of evals and annotator quality, publishing research and translating findings into production datasets.
Lead Protege's DataLab research organization, defining strategy for AI training data quality, evaluation systems, and marketplace optimization while managing researchers and partnering with Product, Engineering, and GTM.
Lead the design and validation of trustworthy benchmarks and evaluations for frontier AI models, including agentic and domain-specific tasks. Own the science of evals and annotator quality, publishing research and translating findings into production datasets.