NVIDIA
Senior Math Libraries Engineer - Sparsity in AI
$184K–$356K
US, CA, Santa Clara +1 · Senior · Full-time · Posted Jun 12, 2026
- Location
- US, CA, Santa Clara
US, Remote - Experience
- 6+ years of overall experience.
- Education
- BS, MS or PhD degree in Computer Science, Applied Math, or related field (or equivalent experience).
About the job
Designs and develops GPU-accelerated libraries and tools for unstructured sparse computing in deep learning and high-performance computing.
What you'll do
- Develop a C++ system for unstructured sparsity on NVIDIA GPUs and enable it in languages and frameworks such as Python and PyTorch.
- Evaluate and improve performance on real-world applications; write tested production code to improve library quality and maintainability.
- Work with partners to understand feature and performance needs and contribute to technical roadmaps.
What they ask for
- BS, MS or PhD in Computer Science, Applied Math, or a related field (or equivalent experience).
- 6+ years developing, debugging, and optimizing high-performance software using C++ and parallel programming.
- Experience with domain-specific language design and compiler optimizations, particularly sparse compilers.
- Excellent C++, Python, and CUDA programming skills.
Nice to have
- Experience with sparse linear algebra and CUDA, MPI, OpenMP, or equivalent technologies.
- Knowledge of sparse computations, AI/HPC, LLMs, deep learning frameworks, GPU performance optimization, numerical linear algebra, or CI/CD practices.
Pay
184,000 USD - 287,500 USD base salary (Level 4); 224,000 USD - 356,500 USD base salary (Level 5)
Tools
C++, Python, CUDA, MPI, OpenMP, MLIR, TACO, PyTorch
AI focus
Develops sparse-computing libraries and tools for deep learning and HPC; enables use through frameworks such as PyTorch. NVIDIA states that it uses AI tools in its recruiting processes.
Model-written summary · the original posting is authoritative