Zoox
Engineering Manager, Performance Optimization
- Location
- Foster City, CA, United States
- Work type
- Hybrid · Full-time
- Salary
- USD 237,000 – 322,000 / year
- Posted
- (6 months ago)
About the role
Zoox is building the world's most advanced self-driving hardware and software solution. The efficiency demands of such a system require an expert fine tuning of both the compute hardware architecture as well as the algorithms and middleware that runs on it to achieve maximum throughput at the most optimal power levels.
The Software Performance team keeps the main onboard computer healthy and performant to ensure that our on-bot autonomy software meets its latency targets while also accommodating its safety goals. We are responsible for the efficient allocation of onboard compute resources (CPU/GPU/Memory/accelerators) ensuring contention is minimized and the autonomy stack executes harmoniously.
As the Onboard Execution team leader within the Performance team, you will lead a highly specialized team of software performance engineers in aggressively optimizing on-bot software runtime. This is a high impact role that sits at the intersection of ML Platform, Core, and Autonomy Software - ensuring that efficient compute utilization is a central tenet emphasized across the organization.
In this role, you will:
Qualifications
- BS in computer science, computer engineering, or related field
- Proficiency with C++ & concurrent (parallel) execution systems
- Deep knowledge and understanding of the Linux operating system and GPU accelerated execution
- Proven track record of cross-functional collaboration and leadership alignment
- Prior experience managing teams of five or more full-time software engineers
Bonus Qualifications
- Hands-on experience with GPU runtime frameworks (CUDA, TensorRT, or XLA)
- Experience in robotics, aviation, automotive, or high-performance computing space
- Have shipped real-time or near-real-time software autonomy or robotics software in production
- Experiencing debugging and optimizing CPU, GPU kernels, and ML models using tools like NVIDIA Nsight Systems and
- Compute, Perfetto or similar compute observability tools