Research Scientist, RL for Autonomous Planning & World Modeling
Core
Developing machine learning solutions for autonomous driving, specifically focusing on reinforcement learning and world models to enable safe vehicle operation in diverse conditions.
Role type
Research Scientist, RL for Autonomous Planning & World Modeling
Builds
Waymo Driver autonomous ride-hail service and internal RL infrastructure
Domain
Autonomous driving / Robotics / Reinforcement Learning
Deliverable
production ML models
Required skills
Reinforcement Learning, Foundation Models, Trajectory Planning, Model Training (Data parallel, FSDP), Distributed Inference, Ablation Studies, Open Source Contributions
Preferred skills
On-policy learning, Human preference alignment, Large-scale training infrastructure, Model sharding/tensor-parallel, Multi-modal learning
Technologies
FSDP, Data parallel, Tensor-parallel, NeurIPS, ICLR, ICRA
Responsibilities
Participate in Waymo's Foundation World Model post-training and evaluation; Research and develop cutting edge RL and Distillation techniques for Autonomous Vehicle Trajectory Planning; Integrate emerging research from the broader AI community into Waymo's internal RL infrastructure; Partner with engineering and research teams to share techniques and best practices.