SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Zoox is building fully autonomous vehicles from the ground up, combining robotics, machine learning, and hardware design. The Software Performance team optimizes the onboard compute stack to ensure autonomy software meets strict latency and safety targets while maximizing efficiency.
As the Onboard Execution team leader within the Performance team, you will lead a specialized team of software performance engineers focused on aggressive optimization of on-bot software runtime. This is a high-impact role at the intersection of ML Platform, Core, and Autonomy Software, ensuring efficient compute utilization is a central organizational priority.
Key Responsibilities:
- Architect onboard GPU execution, defining how perception, prediction, and planning workloads share GPUs, including scheduling, multi-tenancy, isolation, and deterministic latency under contention.
- Drive compute reduction by owning a multi-year roadmap to cut onboard compute per vehicle, setting latency and utilization budgets, and landing major levers across models, runtimes, middleware, and hardware in production releases.
- Shape hardware and platform direction by guiding next-generation compute decisions (GPU and SoC selection, topology, memory budgets) with workload models and performance projections, then leading performance bring-up of each new platform.
- Lead inference performance at scale by setting direction for the inference stack (TensorRT, CUDA, custom kernels, quantization) and partnering with ML teams to ensure models are designed for the hardware they ship on.
- Provide technical leadership by leading and mentoring senior engineers, aligning directors and VPs through design docs, and making critical decisions when performance, safety, and schedule conflict.
Requirements:
- BS in Computer Science, Computer Engineering, or related field, plus 10+ years in systems or performance engineering, including leading GPU or accelerator architecture across teams or building and leading a performance engineering team.
- Deep expertise in CUDA platform (programming model, runtime, driver) and NVIDIA GPU microarchitecture (Ampere through Blackwell, Orin, Thor).
- Proven track record setting technical direction and delivering large, measurable end-to-end gains in latency, utilization, or cost.
- Working knowledge of ML inference optimization (TensorRT, XLA, Triton, quantization, fusion) and expert-level C++ on Linux.
- Ability to align ML, systems, hardware, and leadership on a shared technical plan.
Bonus Qualifications:
- Real-time or embedded GPU experience in autonomy, robotics, AR/VR, games, or HPC.
- Production GPU multi-tenancy experience (MPS, MIG, priority streams).
- New GPU architecture or platform bring-up, benchmarking methodology, or workload modeling and projections.
