Senior GPU Firmware & Fleet-Scale Systems Engineer

NVIDIA; California (MO); On-site; USD 272,000 - 431,250; Full time

Job summary

NVIDIA is seeking a Principal Software Engineer to lead CSP engagement efforts around GPU firmware and system software. You will coordinate with CSP engineering teams to ensure fleet-scale GPU firmware operates reliably, with update orchestration, validation, and secure boot considerations prioritized in the roadmap.

As the technical focal point, you will champion customer feedback into the feature roadmap and enable customer automation and recovery procedures before each release, driving

Qualifications

• 15+ years of experience in GPU system software, GPU firmware, or accelerator platform engineering.
• Deep understanding of GPU architecture internals and performance impact of firmware/driver decisions.
• Understanding of multi-GPU fabric architectures and NVLink coordination.
• Experience with firmware update lifecycles at scale and rollback strategies.
• Familiarity with GPU health telemetry (Xid, thermal, ECC) and security concerns in firmware.
• Proven ability to influence engineering teams and drive fleet-scale improvements.

Responsibilities

• Drive GPU firmware and software work streams with CSP engineering teams and plan delivery roadmaps.
• Synthesize CSP feedback on manageability, observability, and security requirements; champion priorities.
• Lead large-scale GPU firmware update orchestration, sequencing, rollback, and validation.
• Serve as technical focal point between NVIDIA and CSP teams; ensure documentation and integration accessibility.
• Identify cross-CSP GPU SW/FW issues and drive documentation, tooling, and test strategy improvements.

Skills

GPU system software

GPU firmware

Accelerator platform engineering

multi-GPU fabric architectures

VBIOS

InfoROM

firmware update lifecycle management

update sequencing

rollback

Xid telemetry

fleet management

customer collaboration

communication with CSPs

security requirements (attestation, TB

Education

BS or MS in Computer Science or Electrical Engineering, or related field

Tools

firmware tooling

GPU driver stack knowledge

Job description

NVIDIA is seeking a Principal Software Engineer to lead CSP engagement efforts around GPU firmware and system software. You will coordinate with CSP engineering teams to ensure fleet-scale GPU firmware operates reliably, with update orchestration, validation, and secure boot considerations prioritized in the roadmap.

As the technical focal point, you will champion customer feedback into the feature roadmap and enable customer automation and recovery procedures before each release, driving