Jobs at Zoox

Lead ML Performance Optimization for autonomous driving, collaborating across teams, implementing optimization techniques, and mentoring engineers for career growth.

As a Senior Software Engineer - C++ GPU Performance, you will optimize GPU algorithms, monitor performance metrics, and influence design decisions for self-driving technology.

The role involves optimizing GPU-based algorithms, developing benchmarking frameworks, analyzing performance metrics, and facilitating efficient code development for autonomous vehicle systems.

Design and optimize on-vehicle perception inference: allocate CPU/GPU resources, compress and quantize large multimodal models, build TensorRT model conversion pipelines, and deliver production-quality low-latency C++/CUDA inference for power- and thermal-constrained vehicle SoCs.

Design and maintain high-speed GPU-based simulation platform ensuring deterministic execution, low latency, and reproducibility at scale. Own interfaces to the self-driving stack, optimize performance, and build self-serve systems to accelerate ML and autonomy workflows while collaborating with ML experts to bridge fidelity gaps.

Develop and optimize a high-speed GPU-based simulation framework for ML training and validation. Apply reinforcement learning to solve behavior and path-planning challenges, bridge sim-to-sim and sim-to-real fidelity gaps, enable self-serve data generation for autonomy users, and write production-ready code integrating ML into core simulation architecture.

As a Senior Software Engineer in 3D Simulation Applications, you'll collaborate with teams to develop scalable simulations for autonomous systems, integrating ML models and improving products based on customer feedback.

The Staff Software Engineer will design and implement web applications for Zoox's autonomous ride-hailing service, mentor junior engineers, and provide architectural leadership across various domains.

Own and enhance Zoox's Bazel-based build ecosystem for a large polyglot monorepo: optimize build pipelines, develop Starlark rules and tooling, integrate quality tools, and build dashboards to improve developer velocity and reliability.