Hardware System Diagnostic Engineer
Core
Define, design, and own the end-to-end diagnostics test suite for manufacturing, debugging, and deployment of rack-scale AI data center products.
Role type
Senior IC hardware system diagnostic engineer
Builds
Diagnostic tools and test suites for accelerator boards and racks
Domain
Hardware systems / AI data center infrastructure
Deliverable
production ML models
Required skills
Python, C/C++, PCIe, memory hierarchies, power management, Linux system tools, test automation frameworks, manufacturing test management
Preferred skills
AI accelerator/GPU/ASIC diagnostics, HBM/advanced packaging, rack-scale management (BMC/PDU/IPMI/Redfish), bare-metal diagnostics, error injection frameworks, NPI experience
Technologies
PCIe, HBM, BMC, PDU, IPMI, Redfish, Linux
Responsibilities
Own end-to-end diagnostics test suite for accelerator boards and racks; Develop diagnostic tools covering AI chip, PCIe, HBM, power, and thermal; Define test coverage and pass/fail criteria for manufacturing screening; Enable JDM/ODM partners with documentation, tooling, and hands-on debug support; Triage and root-cause manufacturing test escapes and field failures; Build and maintain CI/CD infrastructure for the diagnostics software stack; Track quality metrics — yield, test coverage, defect density — and report out
Seniority
Senior, hands-on IC
