• Leads the technical evaluation and assurance efforts within our AI Governance team • Establishes enterprise-grade, decision-relevant methodologies for red teaming, testing, and evaluating AI systems across traditional ML, Generative AI, and Agentic AI applications • Develops reproducible frameworks to measure AI value, user impact, and broader outcomes • Designs rigorous evaluation methodologies for assessing AI system performance, safety, reliability, and alignment with intended use across the AI lifecycle • Develops criteria and benchmarks to determine whether existing evaluations are adequate and sufficient for different AI applications and risk profiles • Designs and executes comprehensive red team exercises to identify vulnerabilities, failure modes, and unintended behaviors across diverse AI systems • Establishes standards for evaluation coverage, rigor, and documentation across the AI lifecycle • Advances the scientific understanding of AI evaluation and safety through white papers and trainings • Provides technical leadership and mentorship to scientists, engineers, and compliance professionals while building organizational evaluation capabilities • Stays at the forefront of AI safety research and identify novel risks emerging from advanced AI capabilities • Translates complex technical findings into actionable recommendations for leadership, governance boards, and cross-functional teams • Collaborates with external researchers, institutions, and industry partners to advance evaluation methodology