Description
Cowboy Space Corporation is hiring a GPU RAS Validation Engineer to own the end-to-end reliability, availability, and serviceability validation strategy for GPU server systems operating in Low Earth Orbit. The role partners with GPU and HBM silicon vendors, analyzes hardware failures, characterizes fault propagation through firmware and operating systems, validates BMC and out-of-band management interfaces, and drives root-cause analysis and test coverage. It requires a bachelor’s degree in electrical engineering or a related discipline, at least five years of hardware, platform reliability, or silicon validation experience, and knowledge of CPU and GPU architectures, RAS concepts, fault injection, and system-management protocols. The position is based in San Carlos or Seattle and offers an annual salary of $150,000–$225,000 plus equity and benefits.
