GPU Software Engineer: Open-Source AI Libraries

Advanced Micro Devices, Inc.; San Jose (CA); On-site; USD 150,000 - 230,000; Full time

Benefits offered by this job

AMD benefits

Job summary

Advanced Micro Devices, Inc. (AMD) is seeking passionate Software Engineers to help build the AI software powering the world’s fastest supercomputers and data centers. You will contribute to open-source AMD projects and collaborate with the broader community to push AI performance and efficiency.

You will work on ROCm, Ray, Triton Inference Server, and other open-source endeavors, developing scalable, high-quality code and enabling AI workloads on data center GPUs across platforms.

Qualifications

• Strong programming skills in C++ and Python.
• Experience with open-source software development and collaboration.
• Familiarity with AI training, inference, and tool development lifecycle.

Responsibilities

• Open-Source Innovation: Contribute to ROCm, Verl, Ray, Triton Inference Server, FlashInfer, and other emerging AI projects.
• Ecosystem Collaboration: Work with partners and communities to enable AI workloads and optimize data center GPU performance.
• AI Tool Engineering: Build internal AI utilities and workflows, leveraging LLMs to accelerate code generation and debugging of GPU performance bottlenecks.

Skills

C++

Python

Open-source collaboration

Education

Bachelor’s or Master’s degree in CS/CE/EE

Tools

CUDA

HIP

OpenCL

Job description

Advanced Micro Devices, Inc. (AMD) is seeking passionate Software Engineers to help build the AI software powering the world’s fastest supercomputers and data centers. You will contribute to open-source AMD projects and collaborate with the broader community to push AI performance and efficiency.

You will work on ROCm, Ray, Triton Inference Server, and other open-source endeavors, developing scalable, high-quality code and enabling AI workloads on data center GPUs across platforms.