Senior System Software Engineer - Hardware Diagnostics & AI

NVIDIA; Durham (NC); On-site; USD 180,000 - 240,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA is seeking a senior system software engineer to own major parts of low-level diagnostic software for next‑generation data center GPUs and rack-scale AI systems.

You will architect, implement, and debug critical components, lead multi‑engineer efforts, and mentor peers while collaborating with hardware architects, driver teams, and field engineers to bring up new hardware and diagnose failures.

Qualifications

• Degree in Electrical/Computer Engineering or Computer Science or equivalent.
• 12+ years in embedded software, firmware, or silicon bring-up.
• Experience leading complex software projects interfacing with hardware.
• Strong C/C++ and Python programming skills.
• Experience with hardware interfaces, device drivers, and low-level debugging.
• Background with PCIe, NVLink, or related networking tech.

Responsibilities

• Architect, implement, debug, and maintain diagnostic software for complex hardware.
• Lead multiple engineers, mentor team, and coordinate cross-functional work.
• Interface with hardware blocks, Linux drivers, registers, and telemetry.
• Define diagnostic and stress strategies for validation, manufacturing, and field use.
• Develop low-level and higher-level workloads using CUDA, GEMM, NCCL, PyTorch.
• Investigate and diagnose memory, ECC, thermals, and high-speed interface issues.

Skills

C/C++

Python

Embedded software

Linux device drivers

Leadership

HW validation

Education

BS or MS in EE/CS

Tools

CUDA

GEMM compute

Job description

NVIDIA is seeking a senior system software engineer to own major parts of low-level diagnostic software for next‑generation data center GPUs and rack-scale AI systems.

You will architect, implement, and debug critical components, lead multi‑engineer efforts, and mentor peers while collaborating with hardware architects, driver teams, and field engineers to bring up new hardware and diagnose failures.