Lead System Debug Engineer, AI & HPC Rack Validation

AMD; Austin (TX); On-site; USD 180,000 - 240,000; Full time

Job summary

AMD in Austin, TX seeks a Lead System Debug Engineer – AI Rack Validation to join the post-Si debug team, driving scalable, automated solutions for system-level debug of AMD EPYC Server and Instinct products.

You will lead cross-functional debug efforts, partner with engineering and manufacturing, and own strategy to improve throughput and milestone delivery in a global, fast-paced environment.

Qualifications

• Must have a strong background in validation roles involving debugging OS, firmware, silicon and hardware issues.
• Experience with analyses of system-level issues and triage across cross-functional teams.
• Bachelors or Masters in electrical or computer engineering with 15+ years of applicable experience.

Responsibilities

• Debug issues found during Silicon bring-up, Systems Validation, and production phases of SOC programs.
• Lead complex debug efforts to identify root cause and resolution.
• Ensure issues are solved on time with quality.
• Manage and track technical issues, risks and priorities to un-gate program milestones.
• Publish debug program indicators and drive changes to improve throughput.
• Coordinate with customers and executives on program status, risks and opportunities.
• Drive technical innovation to improve AMD’s capabilities across triage, debug, tooling, and methodologies.
• Collaborate with global teams across time zones.

Skills

Analytical skills

Problem solving

Communication

Validation

System debug

OS handoff

Driver/BIOS interaction

X86 architecture

SoC design

Memory, RAS, power management

Education

Bachelors or Masters in electrical or computer engineering

Tools

PCIe

CXL

System debug tools

Job description

AMD in Austin, TX seeks a Lead System Debug Engineer – AI Rack Validation to join the post-Si debug team, driving scalable, automated solutions for system-level debug of AMD EPYC Server and Instinct products.

You will lead cross-functional debug efforts, partner with engineering and manufacturing, and own strategy to improve throughput and milestone delivery in a global, fast-paced environment.