The opportunity
Waymo is an autonomous driving technology company with the mission to be the world's most trusted driver. Since its start as the Google Self-Driving Car Project in 2009, Waymo has focused on building the Waymo Driver—The World's Most Experienced Driver™—to improve access to…
What you'll do
Literature research of SOTA in RSI, physics AI foundational models,: autonomous driving foundational models, World Action models and connect the SOTA to their research projects to improve driver quality
Design new data and post-training recipe to RL the driver with the critic: model and world model in a close loop setup
Coding and implementing the RSI system
Inspect training results and ablation studies to iterate the algorithm design
Currently pursuing a PhD in Computer Science, Robotics, Machine Learning, or a related quantitative field
Depth in foundational AI model post-training, especially RL
What they're looking for
- Fluency in using AI coding agents, fluency in one of the RL training framework such as Rex, Verl, NeMo-RL
- Fluency in AI model training basics such as transformer architecture, hyperparameter tuning, overfitting debug
- Familiarity with autonomous driving, physics AI, VLA, or world models
- Depth in RL for robotics or autonomous driving models
