GPU boards Failure Analysis Engineer

Advanced Micro Devices, Inc • Austin, TX

1d

About The Position

The Quality Returns Debug Team is seeking an experienced GPU PCBA Debug and Failure Analysis Engineer. The engineer will perform board-level failure analysis on customer and factory failures of GPU accelerators, reproduce reported failures, isolate causes, and work with cross-functional engineering teams to identify root causes and corrective actions. The role contributes to product quality, reliability, and customer satisfaction. The ideal candidate brings analytical problem-solving skills, hands-on technical experience, system integration and High Performance Computing experience, strong communication and documentation skills, initiative, adaptability, and the ability to manage multiple tasks with limited supervision. The role is not eligible for visa sponsorship.

Requirements

• Experience in GPU PCBA debug and failure analysis.
• Strong analytical problem-solving skills and a hands-on approach.
• Experience with system integration and High Performance Computing.
• Ability to work collaboratively and independently, manage multiple tasks with limited supervision, and adapt to a fast-paced environment.
• Strong communication, documentation, and presentation skills.
• Persistence and thoroughness in failure analysis and repair.
• Proficiency in Python and shell scripting, and experience working in Windows and Linux environments.
• Ability to read schematics and interpret datasheets, identify components, and perform soldering and rework for debug.
• Proficiency in MS Excel for data analysis and reporting.

Nice To Haves

• Deep expertise in GPU architecture, including debug, validation, and stress or functional test development.
• Skill using lab equipment such as oscilloscopes, logic analyzers, and custom test tools for hardware validation.
• Strong background in PCBA diagnostics, failure analysis, and debug techniques from NPI through production.
• Understanding of firmware, drivers, and hardware interactions, including ability to tune firmware as needed.
• Extensive experience in hardware verification and system integration.
• Familiarity with PCBA manufacturing processes and IPC-A-610 quality standards.
• Hands-on experience assembling, installing, and configuring computer systems and servers.
• Knowledge of high-speed digital design, HBM and GDDR memory interfaces, PCIe, and display outputs such as DP and HDMI.
• Experience with GPU data center infrastructure and AI/ML technologies.

Responsibilities

• Troubleshoot PCBA-level AMD GPU product failures in response to internal and external requests, supporting yield and quality improvements and customer quality needs within expected timelines.
• Develop and execute design-of-experiments tests to reproduce and isolate difficult-to-find failures.
• Develop automation and tools to run tests and analyze results and logs.
• Perform triage and communicate with contract manufacturers and internal teams—including Design, BIOS, firmware, memory, I/O, display, diagnostics, Test Engineering, and Board Operations—to reproduce failures and identify root causes.
• Document findings in the failure analysis database and prepare complete failure analysis reports for customers as needed.
• Present findings to key stakeholders, including senior management.
• Improve failure analysis processes and techniques, and create procedures describing the steps to follow.
• Oversee setup of new products and test stations for Failure Analysis operations.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed