GPU System Reliability Engineer Lead

About the role

The role focuses on ensuring the reliability of high‑performance GPU compute systems operating in Low Earth Orbit. You will lead the end‑to‑end RAS (Reliability, Availability, Serviceability) validation strategy, working closely with GPU and memory silicon partners to detect, classify, contain, and recover from faults autonomously.

Key responsibilities

• Lead RAS validation strategy and execution for GPU server platforms, including fault injection, detection coverage, and recovery verification.
• Partner with GPU system designers to analyze hardware failures, review silicon errata, and define fault‑handling requirements for DDR, HBM, CPU, and GPU subsystems.
• Characterize fault propagation paths across firmware and OS layers and validate error signal classification, logging, and remediation.
• Validate BMC and out‑of‑band management visibility via IPMI, Redfish, and MCTP/PLDM protocols.
• Debug complex failure modes spanning GPU/CPU architecture, memory subsystems, PCIe/NVLink fabric, and system management firmware.
• Drive root‑cause analysis for RAS failures and provide input on platform design decisions.
• Define RAS coverage metrics and maintain traceability from hardware fault models to test coverage.
• Collaborate with firmware, software, and platform teams to validate OS‑level error handling, ACPI interfaces (EINJ, BERT, HEST), and runtime recovery flows.

Required profile

• Bachelor’s degree in Electrical Engineering or a related discipline.
• 5+ years of experience in system‑level validation, hardware reliability, or related fields.

Required skills

• GPU architecture and HBM memory knowledge.
• DDR memory, PCIe, and NVLink expertise.
• BMC management, IPMI, Redfish, MCTP/PLDM protocols.
• ACPI error interfaces (EINJ, BERT, HEST).
• Fault injection and root‑cause analysis.
• Firmware and OS‑level debugging.