Lead GPU Dense Linear Algebra Kernel Engineer

NVIDIA Corporation; Santa Clara (CA); Hybrid; USD 190,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Hybrid work model

Job summary

NVIDIA Corporation is seeking software engineers to design, develop, and optimize GPU-accelerated dense linear algebra kernels for libraries like cuSOLVER. You will lead and collaborate across teams to meet performance goals while advancing accelerated computing methods.

Ideal candidates have 5+ years of experience with C++, CUDA, and parallel programming, plus strong numerical methods fundamentals. This role offers a hybrid work model and opportunities for equity and benefits.

Qualifications

• PhD or MSc in Computational Science and Engineering, Computer Science, Applied Mathematics, or related field (or equivalent experience).
• 5+ years of experience in developing, debugging and optimizing high-performance numerical linear algebra software using C++ and parallel programming; ideally CUDA, MPI, OpenMP, OpenACC, pthreads.
• Strong fundamentals in numerical methods such as computational linear algebra, linear system solvers, eigenvalue and singular value decompositions.
• Experience developing dense linear algebra libraries such as BLAS, LAPACK; and parallel counterparts like PBLAS and SCALAPACK.
• Strong collaboration, communication, and documentation habits.

Responsibilities

• Design, implement and optimize scalable high-performance numerical dense linear algebra software on GPUs.
• Provide technical leadership to library engineers, QA engineers, and interns.
• Collaborate with product management and partners to define feature and performance requirements and roadmaps.
• Identify opportunities to improve library quality, performance and maintainability through architectural improvements.

Skills

CUDA

MPI

OpenMP

OpenACC

Pthreads

Strong collaboration

Documentation

Education

PhD in Computational Science and Engineering

MSc in Computational Science and Engineering

Tools

BLAS

LAPACK

PBLAS

SCALAPACK

Job description

NVIDIA Corporation is seeking software engineers to design, develop, and optimize GPU-accelerated dense linear algebra kernels for libraries like cuSOLVER. You will lead and collaborate across teams to meet performance goals while advancing accelerated computing methods.

Ideal candidates have 5+ years of experience with C++, CUDA, and parallel programming, plus strong numerical methods fundamentals. This role offers a hybrid work model and opportunities for equity and benefits.