Manager - Model Evaluation
Core
Lead an engineering and data science team to evaluate, benchmark, and validate machine learning models and behavioral algorithms for autonomous vehicle prediction and planning stacks.
Role type
Manager, Model Validation & Verification (VnV)
Builds
Statistical frameworks, offline/online evaluation metrics, and validation pipelines for AV behavioral models
Domain
Autonomous Vehicles, Machine Learning, Safety Engineering
Deliverable
production ML models
Required skills
Team leadership, statistical frameworks, offline/online evaluation, simulation benchmarking, release gating, cross-functional partnership, executive communication
Preferred skills
Autonomous vehicles experience, large-scale simulation infrastructure, reinforcement learning, generative AI
Technologies
Python, C++, simulation frameworks, ML evaluation pipelines
Responsibilities
Lead and mentor a team of Data Scientists, ML Validation Engineers, and Software Engineers; Define and execute end-to-end validation strategies across offline evaluation, simulation, and shadow-mode fleet benchmarking; Oversee metric development and standardization to establish quantitative go/no-go release criteria; Partner with Planner, Prediction, MLOps, and Developer Efficiency teams to streamline pipelines; Translate complex model performance trade-offs and safety risks into data-driven recommendations for executive leadership
Seniority
Manager, hands-on leadership
