Failure Analysis Engineer - Power & Thermal

About the role

The Quality Engineering team at AMD is seeking a Failure Analysis Engineer with expertise in Power and Thermal, focusing on supporting customer and factory failure investigations for GPU accelerators. The primary responsibilities include triaging and isolating failures on PCBs, developing diagnostics, and collaborating with various teams to accelerate root cause analysis and corrective actions.

Responsibilities

• Support internal and external requests to troubleshoot AMD GPU product failures, with a primary focus on Power and Thermal failure analysis, PCB triage, and board-level failure isolation.
• Develop and execute diagnostics, scope-based measurements, and functional test DOE’s to reproduce, characterize, and isolate difficult board-, power-, and thermal-related failures.
• Develop Automation and tools to run tests and analyze results/logs.
• Perform structured PCB triage by narrowing failures to the board, component, power rail, layout interaction, or system integration level, and work with the contract manufacturer and internal AMD teams to reproduce failures, isolate root cause, and determine the most effective next steps for debug and corrective action.
• Use schematics, layout data, lab measurements, and power/thermal behavior knowledge to understand system behavior, trace likely fault paths, form debug hypotheses, and build targeted validation plans that drive efficient fault isolation and high-quality failure analysis.
• Analyze liquid-cooling performance and thermal dissipation behavior, including flow-related conditions, heat transfer effectiveness, and cooling-path anomalies, to support efficient root cause analysis of Power and Thermal failures.
• Document all findings into FA database and create a complete failure analysis report for customer consumption as needed.
• Present findings to key stakeholders, including senior management.
• Implement ongoing continuous improvements of failure analysis process & techniques and create procedures of the steps to follow.
• Oversee the set-up of new products and test stations for Failure Analysis operations.

Requirements

• Deep expertise in hardware debug fundamentals, Power and Thermal failure analysis, diagnostics, and structured failure reproduction, including functional test development.
• Skilled in using lab equipment (oscilloscopes, logic analyzers, power analyzers, and custom test tools) to capture scope shots, validate rails, characterize thermal behavior, and support hardware debug.
• Working knowledge of liquid-cooling systems and thermal management concepts, including flow rates, heat dissipation, thermal transfer, and cooling loop behavior in high-power server environments.
• Strong background in PCB triage, board-level failure analysis, schematic review, diagnostics, and failure isolation techniques, with added experience debugging power and thermal issues from NPI through production.
• Proficient in Python, shell scripting, and working across Windows and Linux environments.
• Solid understanding of firmware, drivers, and hardware interactions, with the ability to tune firmware as needed.
• Extensive experience in hardware verification and system integration.
• Hands-on experience assembling, installing, and configuring computer systems and servers.
• Strong communication, documentation, collaboration, and presentation skills.
• Able to read schematics, interpret datasheets, identify components, and perform soldering/rework to support efficient hardware debug and failure isolation.
• Knowledge of high-speed digital design, power delivery networks, voltage regulator behavior, memory interfaces (HBM, GDDR), PCIe, and display outputs (DP, HDMI).
• Experience with GPU data center infrastructure and AI/ML technologies is a plus.

Qualifications

• Bachelor’s degree in Electrical Engineering, Computer Engineering, or a related field.

Skills

• Python
• Shell scripting
• Linux environment
• High-speed digital design
• Power delivery networks
• Voltage regulator behavior
• Memory interfaces (HBM, GDDR)
• PCIe
• Display outputs (DP, HDMI)

Benefits

AMD benefits at a glance.