Principal Software Engineer, GPU Firmware

Job Summary

Driving GPU firmware and system software engagements, the full-time Principal Software Engineer, GPU Firmware will serve as the technical focal point for key CSP/hyperscale customers, ensuring effective management and operation of NVIDIA GPU firmware at scale while collaborating with engineering teams to enhance integration and recovery procedures.

Key responsibilities

• Drive GPU firmware and software work streams with CSP engineering teams, ensuring understanding of architecture, update sequencing, and power management
• Gather and synthesize CSP feedback on GPU firmware/software to influence NVIDIA's feature roadmap and delivery plan
• Oversee GPU firmware update orchestration for large-scale deployments, including validation and failure handling across multiple GPUs

Required qualifications

• 15+ years of experience in GPU system software, firmware, or accelerator platform engineering with a BS or MS in Computer Science, Electrical Engineering, or related field
• Deep understanding of GPU architecture internals and the impact of firmware/driver decisions on performance
• Experience with firmware update lifecycle management at scale, including multi-device update sequencing and emergency recovery
• Knowledge of GPU error handling and recovery flows, as well as health monitoring and telemetry
• Proven ability to influence engineering teams to improve quality and manageability for fleet-scale customers