NVIDIA
System Software Engineer – Data Center GPU Compute Diagnostics
$124K–$196K
US, NC, Durham · Full-time · Posted Oct 21, 2026
- Experience
- 2+ years in one or more of the stated fields.
- Education
- BS or MS degree in Electrical Engineering, Computer Engineering, Computer Science, or a related field, or equivalent experience.
About the job
Develop low-level diagnostic and stress software to validate data center GPUs and rack-scale AI systems, from hardware bring-up through field support.
What you'll do
- Develop diagnostics and stress tests in C/C++ and Python, and interface with hardware, firmware, Linux drivers, registers, and debugging tools.
- Bring up and validate new silicon; investigate hardware and software failures across compute, memory, interfaces, power, and thermal behavior.
- Create targeted validation workloads and collaborate with hardware, driver, silicon-validation, manufacturing, and field teams.
What they ask for
- BS or MS in Electrical Engineering, Computer Engineering, Computer Science, or a related field, or equivalent experience.
- 2+ years in embedded software, firmware, Linux device drivers, systems software, hardware validation, diagnostics, or silicon bring-up.
- Strong C and C++ programming skills and working proficiency in Python.
- Experience developing hardware-interacting software and creating diagnostics, validation, stress, manufacturing, or failure-isolation tests.
Pay
124,000 USD - 195,500 USD base salary
Tools
C, C++, Python, Linux, CUDA, GEMM, NCCL, PyTorch
AI focus
Develop diagnostics and stress workloads that may include higher-level AI workloads; use AI-assisted tools where appropriate for coding, debugging, test creation, and failure analysis.
Model-written summary · the original posting is authoritative