Role Overview
Waymo builds the Waymo Driver, a fully autonomous driving system. The Driver Refinement Foundations team provides the common framework for post-training and heuristic hill climbing across the Planner organization, building platforms that deliver driving behavior improvements using data-driven and heuristic methods. This is a hybrid onsite internship.
Responsibilities
- Mine and curate dataset samples from large corpora of driving data
- Leverage large language models and world foundation models for reasoning, decision making, and multi-modality generation
- Design and implement robust data generation pipelines
- Design and evaluate experiments for model training
Requirements
- Currently enrolled in a graduate program (Master's or PhD) in Computer Science or a related technical field
- Strong problem solving and programming skills in Python and/or C++
- Good understanding of Jax/PyTorch
- Experience in model evaluation and understanding metrics
- Experience in strong software engineering principles
Nice to Have
- Some understanding of SQL (preferred, not required)
- Previous internship experience
- PhD preferred