NVIDIA
Data Center
SystemSoftwareEngineer–DataCenterGPUComputeDiagnostics
Neural analysis suggests this role is
optimal for Mid candidates.
“System Software Engineer – Data Center GPU Compute Diagnostics at NVIDIA. Skills: System software, GPU diagnostics, CUDA, GEMM workloads, Low-level diagnostics, Hardware validation. Build applications and compute workloads that test and heavily stress GPU compute engines, HBM memory, cache hierarchy, PCIe/NVLink interfaces, power delivery, and thermal behavior. Use those applications in silicon/system bring-up”
What You'll Achieve.
Efficiently validate and test next-generation processors and systems
Industry & Context.
Problem solving; Low-level debugging skills
What They're Looking For.
Must Have
5+ years of system software, GPU software, embedded software, or hardware validation experience, Experience writing low-level diagnostics, interacting with device firmware and hardware level debuggers, C/C++ and Python programming skills, Working knowledge of memory systems, ECC behavior and DMA engines, Familiarity with GEMM-style workloads, Awareness of voltage/frequency characterization, thermal testing, power stress, or related silicon validation concepts such as Vmin/Fmax and P-state testing, Experience using modern AI development and analysis tools to improve engineering velocity, including code development, debugging, and test creation, problem solving and low-level debugging skills
Nice to Have
Exposure to GPU architecture, CUDA kernels, GPU compute workloads, or related accelerator programming is strongly preferred
What You'll Do.
Build applications and compute workloads that test and heavily stress GPU compute engines
PCIe/NVLink interfaces
Use those applications in silicon/system bring-up
Package such tools for manufacturing and customer use
Partner with a senior engineer leading the team's CUDA kernel and GEMM diagnostics work
Own well-scoped pieces of the codebase end-to-end
Ramp on GPU microarchitecture and silicon characterization
Implement and maintain CUDA/C++ diagnostic workloads and software infrastructure
Write and tune GPU compute tests
Implement and tune GEMM-style diagnostic workloads
Contribute to higher-level AI workload tests
Bring up and validate new hardware features
Triage and debug failures
How You'll Work.
Team & Collaboration
Partner with a senior engineer leading the team's CUDA kernel and GEMM diagnostics work; Close collaboration with hardware architecture, silicon validation, manufacturing and field teams; Working closely with hardware architecture, driver, manufacturing, and field teams through the product development lifecycle of rack-scale AI systems
Full Job Description
We are seeking a system software engineer to work on next-generation Data Center GPU diagnostics for rack-scale AI supercomputer systems. Our charter is to build applications and compute workloads that test and heavily stress GPU compute engines, HBM memory, cache hierarchy, PCIe/NVLink interfaces, power delivery, and thermal behavior, and to use those applications in silicon/system bring-up along with packaging such tools for manufacturing and customer use. In this role you will partner with a senior engineer leading the team's CUDA kernel and GEMM diagnostics work, owning well-scoped pieces of the codebase end-to-end while ramping on GPU microarchitecture and silicon characterization. The best candidates will have experience writing low-level diagnostic, performance, or stress software for complex hardware systems, ideally including experience with GPUs, CUDA kernels, GEMM-style workloads, CPUs, NICs or high-speed interconnects such as PCIe. Good interpersonal skills are required as this role will involve close collaboration with hardware architecture, silicon validation, manufacturing and field teams. In addition, the engineer will grow their knowledge of operating systems, computer architecture, GPU memory, voltage/frequency behavior, thermal limits, high-speed buses, and modern AI development and analysis tools to efficiently validate and test next-generation processors and systems. Join an exciting, rewarding and fast paced environment! **What you'll be doing:** * Working closely with hardware architecture, driver, manufacturing, and field teams through the product development lifecycle of rack-scale AI systems. * Implementing and maintaining CUDA/C++ diagnostic workloads and software infrastructure used in chip development, validation, productization, and field triage. * Writing and tuning GPU compute tests that stress Tensor Cores, SMs, L2/cache hierarchy, HBM memory, and related power/thermal operating points. * Implementing and tuning GEMM-style diagnostic
Applying for this System Software Engineer – Data Center GPU Compute Diagnostics role?
Most applicants get filtered before a human reads their resume. See if yours makes the cut.
How to Apply on Workday
- Workday has a multi-step form — save your progress after every section.
- "Apply With LinkedIn" can fail or lose data; manual entry is more reliable.
- Watch for the "Submit for Review" final step — hitting "Save" alone does not submit.
- Job requisition numbers are useful when following up with HR by email.
ANONYMOUS · UNFILTERED
What do employees actually say about NVIDIA?
Real rants from real employees. Read before you apply.