Manager - Model Evaluation

Team Leadership & Execution: Lead, mentor, and scale a high-performing team of Data Scientists, ML Validation Engineers, and Software Engineers while driving roadmaps, sprint execution, resource allocation, and high-throughput model releases with rigorous safety guardrails. Culture of Rigor: Foster a culture of statistical excellence, healthy skepticism, proactive risk tracking, and data-driven decision-making.

Validation Strategy & Methodologies: Define and execute end-to-end validation strategies across offline evaluation, open/closed-loop simulation, and shadow-mode fleet benchmarking to ensure robust behavioral model performance. Statistical uncertainties, and regressions into clear, data-driven recommendations for release gating and executive leadership.

Metrics, Release Gating & Rigor: Oversee metric development and standardization with System Safety and Autonomy teams, establishing quantitative go/no-go release criteria for Behavioral Planner and Prediction ML models while fostering statistical rigor and proactive risk management.

Cross-Functional & Infrastructure Partnership: Partner closely with Planner, Prediction, MLOps, and Developer Efficiency teams to translate behavioral requirements into measurable validation targets, streamline dataset and evaluation pipelines, and optimize runtime and compute costs.

Executive Communication & Decision-Making: Translate complex model performance trade-offs, statistical uncertainty, regressions, and safety risks into clear, data-driven recommendations for release decisions and executive leadership.

Experience with autonomous vehicles, robotics, or other safety-critical systems.

Experience building large-scale simulation, model evaluation, or validation infrastructure.

Experience with reinforcement learning, generative AI, or distributed ML systems.