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
Implement, train, and evaluate generative models (such as diffusion models,: flow matching, or autoregressive transformers) for video and physical world simulation.
Experiment with unified 3D/4D and spatiotemporal representations that: generalize across diverse scenes, vehicle platforms, and sensor modalities.
Investigate conditioning, fine-tuning, or distillation methods to improve: temporal consistency, physical realism, and inference speed for closed-loop simulation.
Partner with mentors and researchers across Waymo and frontier AI labs at: Google to adapt foundation world models and translate research prototypes into Waymo’s simulation pipeline.
Currently pursuing an MS or PhD in Computer Science, Machine Learning,: Computer Vision, Robotics, or a related field.
Solid background in deep learning and computer vision, with hands-on: experience in modern generative modeling (e.g., diffusion models, flow matching, VAEs, or transformers).
What they're looking for
- Strong coding skills in Python and practical experience training and debugging models in PyTorch or JAX.
- Prior research or projects in video generation, world models, or generalized 3D/4D scene representations.
- Exposure to 3D computer vision, multi-view geometry, physical/geometric: priors, or multimodal sensor data (Camera, LiDAR, Radar).
- Contributions to open-source projects or publications in ML, vision, or: robotics venues (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML).
