GPU Performance Engineer - CUDA for Real-Time Robotics

Lever, Inc.; Foster City (CA); On-site; USD 237,000 - 298,000; Full time

Job summary

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.

Qualifications

• BS in computer science or related field and 3+ years of experience.
• Strong knowledge of CUDA as applied to recent GPU microarchitectures (e.g., Ampere, Blackwell) and experience debugging/optimizing GPU kernels using tools like Nsight.
• Strong knowledge of C++ and experience in large code bases, comfortable in Linux development environments.
• Experience in development, debugging, and profiling of complex multiprocess systems (e.g., robotic systems, game engines).

Responsibilities

• Analyze performance metrics to identify GPU hotspots and optimizations
• Contribute to the adaptation of our current planner to multiple GPU architectures with different resources
• Optimize ML models for latency and GPU memory usage
• Support engineers within Planner as a subject matter expert on CUDA & GPU performance

Skills

CUDA knowledge

C++ expertise

Linux development

GPU performance debugging

Multiprocess systems

Education

BS in computer science or related field

Tools

Nsight

CUDA toolkit

Job description

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.