Waymo is looking to solve research problems related to scene reconstruction and understanding from real-world scenarios, leveraging geometric foundation models and/or vision-language foundation models to advance autonomous driving technology.
Requirements
- Hands-on computer vision and machine learning experience (prior internships or coursework)
- Related publications in major conferences (e.g. CVPR, ICCV, ECCV, NeurIPS, ICLR, etc) or ongoing research projects in this area
- Strong software engineering skills (Python, C++)
- Prior experience in feed-forward scene reconstruction methods (e.g., VGGT) and vision-language foundation models
- Ability to rapidly prototype research ideas in deep learning frameworks (e.g. TensorFlow, PyTorch, JAX)
Responsibilities
- Solve research problems related to scene reconstruction and understanding from real-world scenarios, leveraging geometric foundation models and/or vision-language foundation models
- Prototype and iterate on various research ideas using Waymo's internal driving data
- Present research findings to a wide audience within Waymo, with the possibility of publishing results to the research community
Other
- Currently pursuing a PhD degree in computer science or a related technical field
- Help solve challenging problems with a direct impact on the company
- Competitive compensation packages with a housing/relocation bonus (if applicable)
- Medical, dental, and vision insurance
- Fun intern events and networking opportunities
