Cowboy Space
GPU System Reliability Engineer Lead
$150K–$225K
San Carlos, California · On-site · Full-time · Posted Sep 21, 2026
- Experience
- 5+ years in hardware validation, platform reliability engineering, or silicon validation on server-class compute systems.
- Education
- Bachelor’s degree in Electrical Engineering or a related discipline.
- Visa sponsorship
- Applicants must be a U.S. citizen, lawful permanent resident of the U.S., protected individual as defined by 8 U.S.C. 1324b(a)(3), or eligible to obtain required authorizations from the U.S. Department of State.
About the job
Leads reliability, availability, and serviceability (RAS) validation for GPU server platforms, ensuring faults are detected, classified, contained, and recovered from across hardware, firmware, and software.
What you'll do
- Lead fault-injection, detection-coverage, and recovery verification; define RAS coverage metrics and test traceability.
- Analyze hardware failures and fault propagation across CPU, GPU, memory, firmware, OS, and management interfaces; drive root-cause analysis with partners.
- Validate BMC and OS error handling, health-event visibility, and runtime recovery flows.
What they ask for
- Bachelor’s degree in Electrical Engineering or a related discipline.
- Deep understanding of CPU/GPU architecture, memory subsystems, cache hierarchies, interconnect fabrics, and RAS concepts.
- Hands-on fault-injection experience at hardware, firmware, and software levels; familiarity with BMC, IPMI, Redfish, and MCTP/PLDM.
- Experience with silicon vendors or ODM partners and strong scripting skills in Python or equivalent.
Pay
$150,000 – $225,000 USD annually; base salary
Tools
DDR, HBM, PCIe, NVLink, XGMI, IPMI, Redfish, Python
Model-written summary · the original posting is authoritative