Staff / Senior Machine Learning Engineer, Reinforcement Learning
Core
Develop and productionize reinforcement learning methods for end-to-end autonomous driving models, focusing on improving driving behavior and safety-critical maneuvers like emergency braking and evasive steering.
Role type
Staff / Senior Machine Learning Engineer (Reinforcement Learning)
Builds
End-to-end driving models and learned emergency trajectory models for autonomous vehicles
Domain
Autonomous driving / Robotics / AI
Deliverable
production ML models
Required skills
Reinforcement learning, Behavior cloning, Python, PyTorch, Experimental design, Large-scale data training, Policy optimization, Reward modeling, Simulation evaluation, Software engineering
Preferred skills
Offline reinforcement learning, Imitation learning, C++, CUDA, Distributed training, Motion planning, Vehicle dynamics, Transformer-based models
Responsibilities
Shape and execute the RL roadmap for driving core and safety teams; Develop and evaluate post-behavior-cloning optimization methods; Improve reward models and learning signals; Build robust training and experimentation workflows; Define evidence across offline metrics and on-road evaluation; Productionize successful methods and mentor the team.