Data Center GPU Diagnostics Software Engineer

NVIDIA Corporation; Durham (NC); On-site; USD 152,000 - 242,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA in Durham, NC seeks a system software engineer to develop low-level diagnostic software for data center GPUs and rack-scale AI systems. You will own components from design through validation and field support, collaborating with hardware architects, driver teams, and silicon-validation engineers.

The role emphasizes C/C++ and Python, with opportunities to learn CUDA programming and GEMM-style compute. NVIDIA offers equity and a comprehensive benefits package.

Qualifications

• BS or MS in Electrical/Computer Engineering or CS, or equivalent experience.
• 5+ years of embedded software and Linux device driver experience.
• Strong C/C++ and Python programming skills.
• Experience interfacing with hardware, firmware, drivers, or low-level interfaces.
• Experience creating diagnostics, validation or stress tests to isolate hardware/system failures.

Responsibilities

• Develop diagnostic and stress software in C/C++ and Python for complex hardware systems.
• Collaborate with hardware blocks, firmware, Linux drivers, registers, telemetry, and debugging tools.
• Bring up and validate new silicon and system features on pre-production hardware and software.
• Create tests for compute engines, memory and cache subsystems, DMA, PCIe/NVLink, power, and thermal behavior.
• Investigate hardware/software failures across boundaries and support field diagnostics.

Skills

C/C++ programming

Python programming

Embedded software

Linux device drivers

Diagnostics

Problem solving

Education

BS or MS in Electrical/Computer Engineering or CS

Tools

CUDA

Python debugging tools

PCIe/NVLink debugging tools

Job description

NVIDIA in Durham, NC seeks a system software engineer to develop low-level diagnostic software for data center GPUs and rack-scale AI systems. You will own components from design through validation and field support, collaborating with hardware architects, driver teams, and silicon-validation engineers.

The role emphasizes C/C++ and Python, with opportunities to learn CUDA programming and GEMM-style compute. NVIDIA offers equity and a comprehensive benefits package.