About the job
Waymo is at the forefront of autonomous driving technology, driven by our mission to become the world's most trusted driver. Originating from the Google Self-Driving Car Project in 2009, we have dedicated ourselves to developing the Waymo Driver—The World’s Most Experienced Driver™—which enhances mobility access and aims to save countless lives lost in traffic accidents. Our Waymo Driver powers a fully autonomous ride-hail service and can be utilized across various vehicle platforms and applications. With over ten million rider-only trips facilitated by our extensive experience of more than 100 million miles driven autonomously on public roads, coupled with tens of billions of miles in simulation tests across 15+ U.S. states, we are redefining the future of transportation.
The Hardware Abstraction Layer (HAL) Optimization team is integral to our operations, utilizing our expertise in CPUs, GPUs, and innovative algorithms to process sensor data at remarkable speeds, feeding it into our Perception models. Our focus lies in a low-level understanding of compute hardware, which we leverage throughout our entire software stack. We are seeking talented engineers with a background in CPU, GPU, or system-level optimization to enhance compute performance both in our vehicles and simulations. Familiarity with compiler technology is a valuable asset. In this role, you will optimize latency and compute utilization across the software stack.
This position follows a hybrid work schedule and reports directly to the Team Lead of the HAL Optimization team.

