Jobs at Zoox

Lead the architecture and strategy for onboard GPU execution in Zoox autonomous vehicles. Define GPU scheduling, multi-tenancy, isolation, deterministic latency, compute budgets, hardware selection, and inference performance direction. Drive end-to-end reductions in latency, utilization, power, and cost across models, runtimes, middleware, and hardware. Provide technical leadership, mentor senior engineers, align cross-functional teams, and lead platform bring-up and performance optimization.

Lead ML training performance for large-scale VLM, VLA, foundation-model, and reinforcement-learning systems. Design distributed parallelism, mixed-precision strategies, gradient checkpointing, GPU kernels, profiling workflows, and performance benchmarks. Own RL optimization strategy and roadmap, diagnose bottlenecks across compute and networking layers, partner with research and engineering teams on architecture, and mentor engineers.

Design, train, and validate machine learning models that improve simulated LiDAR, radar, and camera realism for autonomous vehicle simulation. Build datasets from real and simulated sensor data, integrate 3DGS and NeRF reconstruction, develop generative augmentation methods, define sensor realism metrics, reduce sim-to-real gaps, and mentor engineers and interns.

Develop and validate machine learning models that improve simulated LiDAR, radar, and camera realism for autonomous vehicle simulation. Build datasets from real and simulated sensor data, integrate 3DGS and NeRF reconstruction, apply generative augmentation, define sensor realism metrics, close sim-to-real gaps, and mentor engineers and interns.

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, build, and operate Zoox's HPC platform supporting thousands of concurrent jobs. Modernize infrastructure (Ray, SLURM, Kubernetes, AWS), improve scheduling, autoscaling, multi-region orchestration, capacity planning, profiling, and developer tooling. Lead cross-team initiatives and mentor junior engineers.

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.

Lead a team of software performance engineers to optimize on-bot autonomy software, ensuring performance meets latency targets and develops self-service frameworks for performance optimization.

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