Senior GPU Performance Engineer - Real-Time Autonomy

Front Door Defense; San Diego (CA); On-site; USD 217,000 - 307,000; Full time

Job summary

Zoox is seeking a Senior Software Engineer specializing in GPU performance to optimize real-time autonomous driving workloads across Zoox compute platforms. You will instrument, monitor, and optimize GPU-based algorithms, spanning computer vision and deep learning, impacting future compute platform designs.

Responsibilities include building instrumentation, identifying GPU hotspots, and collaborating on middleware to maximize CPU/GPU efficiency.

Qualifications

• BS in computer science or related field with 7+ years of experience.
• Strong CUDA knowledge and Nsight debugging/optimizing GPU kernels.
• C++ expert with Linux development experience.

Responsibilities

• Build real-time instrumentation for performance monitoring (CPU, GPU, latency, memory) and benchmarking frameworks to evaluate performance at scale.
• Analyze performance metrics to identify GPU hotspots and root causes and propose solutions.
• Support teams on porting serial algorithms to the GPU to maximize compute utilization and reduce latency.
• Contribute to Core team in designing a middleware framework for efficient CPU/GPU code development.

Skills

CUDA

C++

Nsight

Linux

GPU kernels

Performance profiling

Education

BS in computer science

Tools

TensorRT

OpenGL

RocM

Job description

Zoox is seeking a Senior Software Engineer specializing in GPU performance to optimize real-time autonomous driving workloads across Zoox compute platforms. You will instrument, monitor, and optimize GPU-based algorithms, spanning computer vision and deep learning, impacting future compute platform designs.

Responsibilities include building instrumentation, identifying GPU hotspots, and collaborating on middleware to maximize CPU/GPU efficiency.