Senior GPU Dense Linear Algebra Engineer

NVIDIA; Massachusetts; On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA is seeking software engineers to advance dense linear algebra kernels for high-performance libraries like cuSOLVER. You will design, implement and optimize GPU-based numerical software and guide library engineers, QA, and interns to meet performance goals.

Base salaries are disclosed for Level 4 and Level 5; equity and benefits are also offered. The role requires strong C++, CUDA/MPI/OpenMP experience and a solid background in numerical linear algebra.

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 using CUDA, MPI, OpenMP, OpenACC, pthreads.
• Strong fundamentals in numerical methods: linear systems, eigenvalues, singular values, decompositions.
• Experience with dense linear algebra libraries such as BLAS, LAPACK and their parallel counterparts like PBLAS and SCALAPACK.
• Strong collaboration, communication, and documentation habits.

Responsibilities

• Designing, implementing and optimizing scalable high-performance numerical dense linear algebra software on GPUs
• Providing technical leadership and guidance to library engineers, QA engineers, and interns
• Working with product management and partners to understand feature and performance requirements and contribute to roadmaps
• Realizing opportunities to improve library quality, performance and maintainability through re-architecting and innovative practices

Skills

C++

Parallel programming

Collaboration

GPU architecture

Education

PhD or MSc in Computational Science & Engineering / CS / Applied Mathematics

Tools

CUDA

MPI

OpenMP

OpenACC

pthreads

BLAS

LAPACK

Job description

NVIDIA is seeking software engineers to advance dense linear algebra kernels for high-performance libraries like cuSOLVER. You will design, implement and optimize GPU-based numerical software and guide library engineers, QA, and interns to meet performance goals.

Base salaries are disclosed for Level 4 and Level 5; equity and benefits are also offered. The role requires strong C++, CUDA/MPI/OpenMP experience and a solid background in numerical linear algebra.