System Software Engineer – Data Center GPU Compute Diagnostics

About this role

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 workloads,

Apply for this role on NVIDIA’s official careers site.