GPU Performance Engineer - C++/CUDA for Autonomous Vehicles

Front Door Defense; Foster City (CA); On-site; USD 168,000 - 239,000; Full time

Benefits offered by this job

Paid time off

Amazon RSUs

Zoox Stock Appreciation Rights

Health insurance

Long-term disability insurance

Job summary

Zoox is building the world’s most advanced self-driving hardware and software solution. As a GPU performance software engineer within the Software Performance team, you will instrument, monitor, analyze and optimize GPU-based algorithms that are critical for perception workloads.

You will build real-time instrumentation for performance monitoring, analyze GPU hotspots, and co-implement solutions with component teams.

Qualifications

• BS in computer science or related field and 3+ 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, comfortable in Linux development environments.
• Experience in development, debugging, and profiling of complex multiprocess systems (e.g., robotic systems, game engines).

Responsibilities

• Build real-time instrumentation for performance monitoring (CPU, GPU, latency, memory) and develop offline benchmarking frameworks to evaluate performance at scale.
• Analyze performance metrics to identify GPU hotspots and root causes, and propose actionable solutions with component teams.
• Support teams on bringing serial algorithms to the GPU to maximize compute utilization and reduce latency.
• Contribute to designing a middleware framework that promotes efficient and performant code development for CPU and GPU.

Skills

CUDA

C++

Nsight

Linux

Performance analysis

GPU kernels

Education

BS in computer science or related field

Tools

TensorRT

XLA

CUDA toolkit

Job description

Zoox is building the world’s most advanced self-driving hardware and software solution. As a GPU performance software engineer within the Software Performance team, you will instrument, monitor, analyze and optimize GPU-based algorithms that are critical for perception workloads.

You will build real-time instrumentation for performance monitoring, analyze GPU hotspots, and co-implement solutions with component teams.