GPU Performance Architect for Robotic Motion Planning

Zoox; Boston (MA); 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 Planner Compute team, focusing on motion planner components, machine learning inference, and CUDA kernels.

You will identify GPU hotspots, adapt the planner to multiple GPU architectures, and collaborate with engineers to reduce latency and memory usage while profiling with Nsight.

Qualifications

• BS in computer science or related field; 8+ years of experience.
• Strong knowledge of CUDA as applied to recent GPU microarchitectures and experience debugging/optimizing GPU kernels using Nsight.
• Strong knowledge of C++ and experience in large code bases; Linux development environment.

Responsibilities

• Analyze performance metrics to identify GPU hotspots and optimizations.
• Contribute to adaptation of the 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

C++

Nsight

Linux

GPU profiling

Education

BS in computer science or related field

Tools

Nsight Tools

Job description

Zoox seeks an expert in GPU performance to instrument, monitor, analyze and optimize GPU-based algorithms for the Planner Compute team, focusing on motion planner components, machine learning inference, and CUDA kernels.

You will identify GPU hotspots, adapt the planner to multiple GPU architectures, and collaborate with engineers to reduce latency and memory usage while profiling with Nsight.