Evaluate and benchmark new LLM releases across legal, tax, coding, finance and other tasks. Analyze failure modes, maintain model integrations and benchmarking infrastructure, collaborate with research and communications teams, and publish leaderboard results used by startups, enterprises, and research labs.

Lead and set research direction for LLM evaluation methodologies and benchmarks, oversee research portfolio, publish influential work, recruit and grow a research team, and collaborate with enterprise customers and lab partners to build robust, deployment-focused evaluation paradigms.