Senior GPU Libraries Engineer — HPC & ML

Advanced Micro Devices; California (MO); Hybrid; USD 180,000 - 240,000; Full time

Job summary

Advanced Micro Devices in San Jose, CA, seeks a Senior Member of Technical Staff to advance GPU libraries within the ROCm ecosystem. You will collaborate with CPU/GPU teams and apply deep expertise from architecture to implementation, ensuring scalable software for HPC and ML workloads.

You will mentor others, drive architectural discussions, and contribute to the software lifecycle in an agile environment, while navigating evolving hardware-software interfaces.

Qualifications

• Strong C++ engineering skills with GPU acceleration experience.
• Experience with CUDA, HIP, OpenMP, MPI, or OpenCL for HPC workloads.
• Proficiency in Python and AI/ML frameworks.

Responsibilities

• Collaborate across library teams to design, implement, validate, and deliver key software library capabilities with GPU kernel integration.
• Contribute to architecture, design, and documentation with senior engineering staff guiding execution.
• Work with principal staff to develop technical designs considering constraints, performance, and roadmap commitments.

Skills

C++

CUDA

HIP

OpenMP

MPI

OpenCL

Python

AI/ML frameworks

Education

M.Sc. or M.Eng. preferred

Tools

Jenkins

Docker

Kubernetes

Job description

Advanced Micro Devices in San Jose, CA, seeks a Senior Member of Technical Staff to advance GPU libraries within the ROCm ecosystem. You will collaborate with CPU/GPU teams and apply deep expertise from architecture to implementation, ensuring scalable software for HPC and ML workloads.

You will mentor others, drive architectural discussions, and contribute to the software lifecycle in an agile environment, while navigating evolving hardware-software interfaces.