NVIDIA
Senior Systems Software Engineer - GPU Performance at Scale
$184K–$356K
US, CA, Santa Clara +4 · Senior · Full-time · Posted Oct 9, 2026
- Location
- US, CA, Santa Clara
US, NC, Remote
US, TX, Remote
US, Remote
US, CA, Remote - Experience
- 8+ years of applicable experience; no alternative stated.
- Education
- BS in Engineering, Mathematics, Physics, or Computer Science (or equivalent experience); MS or PhD desirable.
About the job
Build and optimize large-scale GPU performance platforms for AI workloads across datacenter hardware and software.
What you'll do
- Implement performance practices, tools, and workflows to validate and improve GPU infrastructure and datacenter products.
- Align AI workloads with new GPU, CPU, and networking systems, collaborating with internal and customer teams.
- Analyze performance and stability issues, identify root causes, and resolve firmware and software problems.
What they ask for
- Understanding of accelerated computing software stacks, including CUDA.
- Programming and scripting experience in C/C++/Python/Bash.
- Expertise in systems architecture and component impacts on performance.
- Experience with modern cloud and container-based enterprise architectures; container technology and Linux-based operating systems; HPC or deep-learning support experience.
Nice to have
- Slurm and Docker.
- End-to-end GPU performance engineering, Linux systems optimization, virtualization or cloud platforms, scheduling/resource management, or large-scale HPC experience.
Pay
184,000 USD - 287,500 USD (base salary, Level 4); 224,000 USD - 356,500 USD (base salary, Level 5)
Tools
CUDA, Slurm, C/C++, Python, Bash, Docker, Linux
AI focus
Optimize performance of AI workloads at scale and align next-generation AI workloads with datacenter systems.
Model-written summary · the original posting is authoritative