This role leads multifunctional teams developing groundbreaking approaches to AI assessment, including automated evaluation systems. You'll work with ML researchers, engineers, and domain experts to pioneer new methods for scalable, high-quality AI evaluation.KEY RESPONSIBILITIES:Lead R&D in automated AI evaluation, including development of LLM-based assessment systems that can reliably evaluate model outputsDrive research and implementation of novel approaches to measure and improve AI system quality, safety, and alignmentBuild and scale evaluation infrastructure that combines human expertise with ML-powered automationWork with cross-functional partners to integrate evaluation systems into production workflows