Fellow - Data Center GPU Systems Design Validation Architect

AMD - Austin, TX

Full-time - Senior

Austin, TX

Computer and Electronic Product Manufacturing

About the position

The Fellow - Data Center GPU Systems Design Validation Architect at AMD is a pivotal role focused on leading the validation of advanced GPU systems, particularly in AI and HPC domains. This position involves orchestrating comprehensive validation strategies to ensure robust system-level integration and performance, while also identifying and mitigating potential product weaknesses. The role requires hands-on technical leadership and collaboration with various teams to develop and execute validation test plans that simulate real-world scenarios.

Responsibilities

• Orchestrating the development and implementation of advanced validation strategies to identify potential product weaknesses.
• Leading a team in pioneering technical validation initiatives focusing on PCIe, HBM, and SMC/BMC firmware.
• Creating and executing validation test plans that address functional and stress scenarios, including emulation of end-customer systems.
• Ensuring compliance with OCP standards and secure solution development, including Out of Band Management and Redfish features.
• Collaborating with multiple teams to devise and execute exhaustive validation test plans that simulate real-world stress scenarios and customer workloads.
• Championing the process of debugging, root cause analysis, and resolution of issues discovered during validation phases.
• Working closely with development teams to ensure all identified issues are addressed before production.
• Advancing end-to-end validation test content utilizing creative debugging skills.

Requirements

• Master's degree in Electrical or Computer Engineering or related field.
• Extensive experience in system architecture and design validation.
• Proficiency in programming/scripting languages such as C/C++, Perl, Ruby, and Python.
• Strong analytical and problem-solving skills with attention to detail.
• Experience with lab equipment such as protocol/logic analyzers and oscilloscopes.
• Ability to lead tasks independently and drive them to successful completion.

Nice-to-haves

• Experience with state-of-the-art debugging techniques and methodologies.
• Deep knowledge in board/platform-level debug including delivery, sequencing, analysis, and optimization.

Benefits

• Employee stock purchase plan
• Annual bonus or sales incentive eligibility
• Competitive benefits package