AI Systems Validation Architect
Role details
Job location
Tech stack
Job description
We are seeking a collaborative and motivated Systems Validation Architect to join our team. In this role, you will develop and execute methodologies and test content for system-level hardware, firmware and software validation on machine learning systems built with AMD's technologies. You'll work closely with architecture, design, and post-silicon teams to identify and resolve complex systems, improving future debug and test features. This position involves developing automation, refining validation processes, executing test cases, analyzing data and driving system-level quality across AMD's product portfolio. We welcome applicants from diverse backgrounds who bring curiosity, technical depth, and a commitment to innovation. THE PERSON: As a Systems Validation Architect, you will deliver our next generation of system tests for our products. In this high visibility position, your systems engineering expertise will be necessary to find and resolve system's HW, FW and SW issues; your SW background will help us advance our test coverage and improve automation frameworks; and your experience with large scale clusters will help us to debug critical issues only seen on scale., * Lead the definition of the test procedures to validate the design of various system components on the next generation of machine learning architectures. This includes all components of servers including CPU/GPU/Memory/BIOS/BMC/IO/storage/networking, etc.
- Lead efforts to validate Scale-up and Scale-out architectures, including definition of test plans at cluster-level as well as writing code to support the validation.
- Translating system specs into a robust system integration test plan.
- Develop complex/critical test content as well as monitoring/debug/root-cause SW mechanisms that others can use in their plans.
- Establish methods to validate, monitor and root-cause errors at cluster-level.
- Make improvements to system level integration test strategies, methodologies, and processes
- Collaboration with customer and multi-functional HW and SW teams to debug and tackle complex issues
- Investigate, profile and enable test content for a wide variety of system domains, as well as benchmarks and proxies for customer workloads into our own test frameworks. These range from industry standard benchmarks to state-of-the-art training and inference applications.
- Develop and improve automation features according to requirements
- Monitor and analyze the execution of automated tests at scale (for hundreds or thousands of systems)
Requirements
- Prior experience working on HPC or Machine Learning HW systems for large data centers
- Several years of experience writing software in languages such as Python and/or C/C++ is a must.
- Post-silicon system integration, system testing
- Debugging skills at SoC (System on a Chip), System level and cluster level.
- Experience with Computer Architecture concepts and silicon features, particularly on machine learning systems (scale-up/scale-out experience is a plus)
- Computer enthusiasts and excellent knowledge of current machine learning technologies in the data center.
- Effective communication skills including influencing and working across large multi-functional HW, SW, architecture teams, * Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent