below marketmost similar roles pay hereabove market
This role pays more than
66%
of similar roles. Most pay
$188,848–$241,750
— the blue band above.
At the midpoint, this role pays about
$236k
versus about
$215k
for comparable roles.
Based on 240 similar postings.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
1623 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 1110 roles with salary data.
The Senior Math Libraries Engineer - Dense Linear Algebra joins the development team focused on dense linear algebra kernels for high-performance libraries like cuSOLVER. This role involves designing, implementing, and optimizing scalable numerical software on GPUs, specifically targeting algorithms such as triangular factorizations, eigenvalue decompositions, and singular value decompositions. The engineer provides technical leadership to library engineers, QA engineers, and interns while collaborating with product management to define technical roadmaps. Key responsibilities include improving library quality and maintainability through re-architecting and innovative software practices. Required skills include C++, CUDA, MPI, OpenMP, OpenACC, and pthreads, alongside expertise in BLAS, LAPACK, PBLAS, and SCALAPACK. The work addresses technical challenges in computational linear algebra, linear system solvers, and large-scale computing technologies like PDE solvers and time-domain simulation methods.
Design, implement, and optimize scalable high-performance numerical dense linear algebra software on GPUs.
Develop and optimize kernels for algorithms including triangular factorizations, eigenvalue decompositions, and singular value decompositions.
Provide technical leadership and guidance to library engineers, QA engineers, and interns on assigned projects.
Collaborate with product management and partners to define feature requirements and technical roadmaps.
Improve library quality, performance, and maintainability through re-architecting and establishing innovative software development practices.
Debug and optimize high-performance numerical linear algebra software using C++ and parallel programming.
What we're looking for
PhD or MSc degree in Computational Science and Engineering, Computer Science, Applied Mathematics, or a related field (or equivalent experience).
5+ years of experience developing, debugging, and optimizing high-performance numerical linear algebra software using C++ and parallel programming.
Experience developing dense linear algebra libraries such as BLAS, LAPACK, and their parallel counterparts like PBLAS and SCALAPACK.
Strong fundamentals in numerical methods including computational linear algebra, linear system solvers, and methods for eigenvalue and singular value decompositions.
Experience developing accelerated computing kernels using CUDA, MPI, OpenMP, OpenACC, or pthreads (preferred).
Good knowledge of CPU and/or GPU hardware architecture (preferred).
Experience with CI/CD systems and project management tools like JIRA (preferred).
Strong background in large-scale computing technologies such as PDE solvers, eigenvalue solvers, or time-domain simulation methods (preferred).