About the job
Waymo is a pioneering force in autonomous driving technology, dedicated to becoming the world's most trusted driver. Originating from the Google Self-Driving Car Project in 2009, Waymo focuses on developing the Waymo Driver—The World's Most Experienced Driver™—to enhance mobility access and significantly reduce traffic-related fatalities. The Waymo Driver powers our fully autonomous ride-hailing service and is adaptable across various vehicle platforms and applications. With over ten million rider-only trips completed and extensive experience from driving more than 100 million miles on public roads, complemented by simulations totaling tens of billions of miles across over 15 U. S. states, we are at the forefront of our industry.
The Large Model Evaluation team plays a crucial role in advancing Waymo's AI ambition. As we leverage advancements in Large Language Models (LLMs) and Vision-Language Models (VLMs), our goal is to create cutting-edge AI systems that navigate the complexities of real-world driving scenarios. Our progress hinges on our ability to measure performance effectively. With robust evaluation being essential for deploying large models, the challenges we face are particularly intricate and safety-critical. We are seeking engineers with a quantitative mindset to explore and establish innovative methods for assessing the machine learning models utilized in the Waymo Driver.

