Senior Software Engineer, Post-Training & RL Frameworks

Waymo is a self-driving technology company seeking a Senior Software Engineer to join its Post-Training & RL Frameworks team. The role involves developing models for autonomous driving, including pre-training and post-training reinforcement learning, scaling models to complex environments, and optimizing the end-to-end training pipeline. This position is critical for Waymo's continued development of its autonomous driving software.

Requirements

• Develop the core training system for adapting RL techniques to unprecedented scales and heterogeneous environments.
• Collaborate with teams to integrate the latest rollout strategies and RL algorithms.
• Improve the end-to-end RL training pipeline for efficient and scalable learners/actors.
• Build evaluations, analyze experimental results, and iterate quickly.
• Stay current with the latest research in RL, Vision-Language-Action (VLA) models, and World models.

Benefits

• Eligible for discretionary annual bonus
• Equity incentive plan
• Generous Company benefits program