NVIDIA
Senior Math Libraries Engineer - Direct Sparse Solvers
$184K–$356K
US, CA, Santa Clara +1 · Senior · Full-time · Posted Jun 9, 2026
- Location
- US, CA, Santa Clara
US, Remote - Experience
- 5+ years of overall experience.
- Education
- PhD or MSc in Computer Science, Computational Science and Engineering, Applied Mathematics, or a related science or engineering field (or equivalent experience).
About the job
Develop GPU-accelerated direct sparse solvers and numerical software for NVIDIA’s cuDSS library, from algorithm and kernel design through testing, release, and support.
What you'll do
- Design, implement, and optimize direct sparse solvers for current and future GPU architectures.
- Collaborate across engineering, QA, product, and partner teams on library development, requirements, and technical roadmaps.
- Improve sparse linear algebra libraries’ quality, performance, and maintainability.
What they ask for
- C++ and parallel-programming experience developing, debugging, and optimizing high-performance numerical software.
- Strong foundations in floating-point arithmetic, numerical analysis, and sparse linear algebra primitives.
- Experience developing, maintaining, and testing scientific computing libraries.
- Strong collaboration, communication, and documentation habits.
Nice to have
- Familiarity with direct-solver methods and CPU/GPU architecture or low-level GPU optimization.
- Experience with CI/CD, JIRA, AI agents, large-scale computing, or globally distributed agile organizations.
Pay
184,000 USD - 287,500 USD base salary (Level 4); 224,000 USD - 356,500 USD base salary (Level 5)
Tools
C++, CUDA, MPI, OpenMP, OpenACC, pthreads, JIRA
AI focus
The role may involve adopting and advancing AI agents in software engineering. NVIDIA states that it uses AI tools in its recruiting processes.
Model-written summary · the original posting is authoritative