I am an AI evals & policy researcher at RAND and a Research Affiliate at Oxford Martin AI Governance Initiative. In Spring 2026, I am collaborating with Cooperative AI Foundation to build multi-agent evaluations. I focus on building the scientific and institutional foundations needed to evaluate increasingly agentic systems — from human baselines and methodological guidance to third-party audit and assurance frameworks. My work has been published at top machine learning venues including ICML, Science, and FAccT, as well as in policy venues including the World Bank, RAND, and Carnegie. I am also the Resilience Section lead of the 2026 International AI Safety Report, Co-founder of NYC AI Governance & Safety, and Faculty at the International Programme on AI Evaluation.