Technical Staff Member, Evaluations

To define and improve evaluations for frontier AI systems, the full-time Member of Technical Staff, Evaluations will design frameworks, develop feedback systems, and conduct research while collaborating with AI researchers and domain experts, with the option to work remotely or from various U.S. locations. Key responsibilities Design and build evaluation frameworks, benchmarks, and methodologies for advanced AI models Develop reward models and feedback systems to make model behavior measurable and improvable Conduct research on evaluation reliability and build systems for high-quality human data Required qualifications PhD in ML/AI, computer science, data science, or related fields, or equivalent industry experience Publications at top AI/ML venues such as NeurIPS, ICML, or ICLR Experience building scalable software and working with agents Strong Python skills and knowledge of frontier AI benchmarks and evaluation techniques Ability to operate in an ambiguous, fast-moving environment with substantial ownership