Senior ROCm Validation Architect

Advanced Micro Devices; San Jose, Northern (CA, KY); Hybrid; USD 200,000 - 260,000; Full time

Job summary

Advanced Micro Devices, Inc. (AMD) in San Jose, CA seeks a Principal Software Engineer to lead ROCm software validation across compute workloads and server-class systems.

You will define validation strategy, build test infrastructure, and drive debugging and qualification for ROCm releases. You will mentor senior validation engineers, collaborate with product management and silicon teams, and influence the roadmap to ensure validation readiness for next-generation Instinct GPUs and servers.

Qualifications

• Experience validating complex systems including multi-GPU and multi-node servers.
• Expert Python for test automation and strong C++ for debugging.
• Experience leading complex validation for ROCm, CUDA, or similar GPU software stacks.
• Experience delivering release-qualification programs for hyperscalers, OEMs, or large customers.

Responsibilities

• Own end-to-end validation architecture for ROCm — unit, integration, workload, and system-level tests across GPU generations and server platforms.
• Define release-qualification gates and exit criteria for ROCm releases and drive teams to meet them.
• Architect the test infrastructure and CI pipelines (GitHub Actions, Jenkins, internal CI) and lab orchestration.
• Mentor and elevate senior validation engineers, SDETs, and QA leads through design reviews and guidance.
• Represent ROCm validation externally through strategic customer engagements and open-source quality initiatives.
• Lead system-level testing for server nodes, multi-GPU topologies, and compute workload validation (LLM training/inference, PyTorch, Triton, JAX).

Skills

Python

C++

Validation

Test automation

Distributed systems

Education

BS/MS/PhD in Computer Science or Computer Engineering

Tools

GitHub Actions

Jenkins

CI pipelines

Job description

Advanced Micro Devices, Inc. (AMD) in San Jose, CA seeks a Principal Software Engineer to lead ROCm software validation across compute workloads and server-class systems.

You will define validation strategy, build test infrastructure, and drive debugging and qualification for ROCm releases. You will mentor senior validation engineers, collaborate with product management and silicon teams, and influence the roadmap to ensure validation readiness for next-generation Instinct GPUs and servers.