RAS Validation Lead - GPU Server Systems (Orbital)

Cowboy Space; San Carlos (CA); Hybrid; USD 150,000 - 225,000; Full time

Benefits offered by this job

Equity in Cowboy Space Corp.

Medical, dental, vision insurance

401(k) retirement savings plan

Paid time off

10 paid holidays per year

Paid parental leave

Relocation assistance

Daily lunch in the office

Job summary

Cowboy Space is seeking a RAS Validation Lead to develop strategy for GPU server validation in Low Earth Orbit. This role involves analyzing hardware failures, characterizing fault propagation, and collaborating with partners to ensure detection mechanisms function effectively.

Ideal candidates have over 5 years of relevant experience and a deep understanding of CPU/GPU architecture along with strong Python scripting skills. The role is based in San Carlos or Seattle and offers competitive compensation.

Qualifications

• 5+ years of experience in hardware validation, platform reliability engineering, or silicon validation.
• Deep understanding of CPU and GPU architecture.
• Strong knowledge of RAS concepts, including ECC and error propagation.
• Hands-on experience with fault injection methodologies.
• Experience working with silicon vendors on hardware failure analysis.

Responsibilities

• Lead RAS validation strategy and execution for GPU server platforms.
• Analyze hardware failures and align on fault handling requirements.
• Characterize fault propagation paths from hardware detection.
• Validate out‑of‑band management visibility into hardware health events.
• Debug complex failure modes spanning GPU and CPU architecture.
• Drive root-cause analysis for RAS failures and provide input on design decisions.

Skills

Hardware validation

Platform reliability engineering

Silicon validation

CPU architecture

GPU architecture

Scripting in Python

Tools

BMC

IPMI

Redfish

MCTP/PLDM

Job description

Cowboy Space is seeking a RAS Validation Lead to develop strategy for GPU server validation in Low Earth Orbit. This role involves analyzing hardware failures, characterizing fault propagation, and collaborating with partners to ensure detection mechanisms function effectively.

Ideal candidates have over 5 years of relevant experience and a deep understanding of CPU/GPU architecture along with strong Python scripting skills. The role is based in San Carlos or Seattle and offers competitive compensation.