GPU Performance Engineer - CUDA for Real-Time Robotics

Zoox seeks an expert in GPU performance to instrument, monitor, analyze and optimize GPU-based algorithms for the motion planner. You will tackle latency-critical workloads, from ML inference to custom CUDA kernels, across multiple GPU architectures.

You will collaborate with the Planner team, optimize ML models for latency and memory, and serve as a CUDA & GPU performance SME for supporting engineers. A BS plus 3+ years in relevant fields is expected, with strong C++ and Linux proficiency.