Lead ROCm Validation Engineer - Multi-GPU Systems

AMD; San Jose (CA); Hybrid; USD 190,000 - 240,000; Full time

Benefits offered by this job

Benefits at a glance

Job summary

AMD in San Jose seeks a Principal Software Engineer to lead ROCm validation across compute workloads and server-class systems. You will define testing strategy, build scalable test infrastructure, and mentor teams to ensure high-quality ROCm releases.

Join a leadership role focused on multi-node validation, LLM training workloads, and performance benchmarking for next-generation Instinct GPUs, in a hybrid San Jose environment.

Qualifications

• Experience leading complex systems validation and quality engineering.
• Expert Python for test automation and infrastructure; strong C++ for debugging and extending production code.
• Deep validation expertise in GPU software stacks, AI/ML frameworks, HPC runtimes, and Linux kernel/drivers.

Responsibilities

• Own end-to-end ROCm validation architecture across multi-GPU generations and server platforms.
• Define release-qualification gates and exit criteria for ROCm software releases.
• Architect the test infrastructure, including distributed test runners, CI fleets, and data lakes.

Skills

Python

C++

Validation

Linux internals

GPU software stacks

CI/CD

HPC/Distributed systems

Education

BS in Computer Science or Computer Engineering

Tools

rocprof

Nsight

Omniperf

GitHub Actions

Jenkins

Job description

AMD in San Jose seeks a Principal Software Engineer to lead ROCm validation across compute workloads and server-class systems. You will define testing strategy, build scalable test infrastructure, and mentor teams to ensure high-quality ROCm releases.

Join a leadership role focused on multi-node validation, LLM training workloads, and performance benchmarking for next-generation Instinct GPUs, in a hybrid San Jose environment.