Senior Math Libraries Engineer - Sparse Linear Algebra
NVIDIAJob Title
Senior Math Libraries Engineer - Sparse Linear Algebra
Role Summary
Design, implement, and optimize sparse linear algebra kernels for NVIDIA's GPU-accelerated libraries (for example, cuSPARSE and cuDSS). The team delivers high-performance numerical software used across AI, data analytics, and scientific and engineering simulations.
Experience Level
Senior; typically requires 5+ years of experience developing and optimizing high-performance sparse linear algebra software.
Responsibilities
The role focuses on implementing and optimizing GPU-accelerated sparse linear algebra algorithms and collaborating with cross-functional teams.
- Design, implement, and optimize scalable sparse linear algebra kernels (sparse BLAS, matrix-vector and matrix-matrix products) for current and future GPU architectures.
- Develop and optimize direct and iterative sparse solvers, preconditioners, and algebraic multigrid (AMG) methods.
- Collaborate with library engineers, QA, product management, and external partners to define feature and performance requirements and contribute to technical roadmaps.
- Improve library quality, performance, and maintainability through refactoring and engineering best practices.
- Mentor and work with interns and other engineers on development, testing, and performance validation.
Requirements
Must-have technical skills and experience.
- 5+ years developing, debugging, and optimizing high-performance sparse linear algebra software using C++ and parallel programming (CUDA, MPI, OpenMP, OpenACC, pthreads, or equivalent).
- Strong fundamentals in floating point arithmetic and implementation of sparse linear algebra primitives.
- Experience developing, maintaining, and testing sparse linear algebra libraries and numerical kernels.
- Strong collaboration, communication, and documentation habits.
Nice-to-have:
- Knowledge of CPU and/or GPU hardware architecture and low-level GPU performance optimization.
- Familiarity with multi-frontal factorizations, iterative solvers, preconditioners, and algebraic multigrid.
- Experience with CI/CD systems and project management tools (e.g., JIRA).
- Understanding of large-scale computing methods such as PDE solvers, eigenvalue solvers, CFD, or FEA, and experience in globally distributed agile teams.
Education Requirements
PhD or MSc preferred in Computational Science and Engineering, Computer Science, Applied Mathematics, or a related science or engineering field; or equivalent practical experience.
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
