Senior Software Development Engineer (diagnostic tests)

THE ROLE: 

Support development and deployment of diagnostic tests that validate AMD Data Center GPU products at all test stages, from silicon screening to server rack assembly.

KEY RESPONSIBILITIES: 

Test Development (60%):

• Design and implement diagnostic tests for AMD silicon and server platforms
• Develop test automation frameworks and infrastructure
• Debug test failures and hardware issues across production stages
• Optimize test coverage and execution time

Cross-Team Coordination (40%):

• Lead root cause analysis and debug efforts for failures on production systems, often in time-sensitive and urgent scenarios
• Interface with silicon design, firmware, performance, systems integration, and manufacturing teams to investigate and resolve issues
• Support manufacturing partners in test bring-up and issue resolution
• Coordinate test deployment schedules and deliverables
• Track and report on test coverage, quality metrics, and production readiness

Additional Duties:

• Participate in code reviews and maintain test code quality
• Document test specifications and deployment procedures
• Occasional lab work and limited factory visits as needed

PREFERRED EXPERIENCE: 

• Proven experience with software development or test engineering experience

• Proven experience with hardware/silicon validation or manufacturing test environments
• Hands-on debugging and root cause analysis in low-level hardware/software systems
• Experience with server or datacenter systems architecture
• Understanding of silicon validation processes and test methodologies
• Familiarity with manufacturing workflows and production test environments
• Knowledge of server architectures (BMC, firmware, system integration)
• Experience with GPU/accelerator performance metrics including computational throughput, memory bandwidth, power efficiency, thermal characteristics, and whole-system performance
• Background in AMD GPU or CPU technologies is a plus
• Strong proficiency in Python and C++
• SQL and Snowflake for data analysis and reporting
• Linux system administration and shell scripting
• Git version control and code review practices
• Experience with diagnostic tools and hardware debugging methodologies
• Knowledge of at least one GPU programming framework (ROCm/CUDA/OpenCL/Vulkan/OpenGL), with ROCm strongly preferred

• Excellent written and verbal communication skills is an absolute
• Ability to document technical designs, test plans, and procedures clearly
• Proven ability to coordinate with cross-functional teams

ACADEMIC CREDENTIALS: 

• BS in Computer Science, Computer Engineering, Electrical Engineering, or related field preferred
• Equivalent experience considered