Own eval strategy and roadmap: prompt set design, scoring methodology, failure-mode taxonomy, and telemetry instrumentation

Coordinate across multiple teams contributing to Build Agent to arbitrate quality standards and drive eval findings to committed, owned fixes — not just reports

Lead model benchmarking efforts, making data-backed recommendations on model support decisions (e.g., evaluating frontier coding models against the incumbent default)

Manage daily activities of an 8-engineer team, including staffing, mentoring, and performance management, while building scale (people, process, or automation) to remove the team as its own bottleneck

Solve ambiguous, cross-cutting problems where evaluation signal, model capability, and platform architecture intersect — and where 'correct' isn't obvious until you've defined the bar

Represent evaluation results and model support recommendations to cross-functional and executive stakeholders, including in response to org-wide benchmark initiatives