2 days ago
Mountain View, CA, USAIntern
H1B sponsor
Responsibilities
- Implement, train, and evaluate generative models for video and physical-world simulation.
- Experiment with unified 3D/4D and spatiotemporal representations across scenes, vehicle platforms, and sensor modalities.
- Investigate conditioning, fine-tuning, and distillation methods to improve temporal consistency, physical realism, and inference speed.
- Collaborate with Waymo and Google researchers to adapt foundation world models and integrate research prototypes into Waymo’s simulation pipeline.
Requirements
- Currently pursuing an MS or PhD in Computer Science, Machine Learning, Computer Vision, Robotics, or a related field.
- Strong background in deep learning and computer vision.
- Hands-on experience with generative modeling, including diffusion models, flow matching, VAEs, or transformers.
- Strong Python coding skills and practical experience training and debugging models in PyTorch or JAX.
- Preferred experience includes video generation, world models, generalized 3D/4D scene representations, 3D computer vision, multi-view geometry, physical or geometric priors, or multimodal sensor data.
- Open-source contributions or publications in ML, vision, or robotics venues such as CVPR, ICCV, ECCV, NeurIPS, or ICML are preferred.
Benefits
- Hybrid onsite internship position.
- Full-time internship with eligibility for the company’s benefits programs, subject to eligibility requirements.
- Applications are accepted on a rolling basis until the role is filled.
Categories
AI ResearchML Engineering
About Waymo
Waymo develops the Waymo Driver, a full-stack autonomous driving system, and operates the Waymo One robotaxi service that offers paid, driverless rides in select U.S. cities. The company monetizes through ride-hailing fares and partnerships integrating its technology on multiple vehicle platforms. Founded in 2009 as Google’s self-driving project, Waymo is headquartered in Mountain View and is an Alphabet subsidiary, with over 10 million rider-only trips and 100+ million autonomous miles on public roads.