Remote GPU Math Libraries Lead - AI & HPC Emulation

NVIDIA Corporation; Polska; Hybrid; PLN 293,000 - 650,000; Full time

Job summary

NVIDIA Corporation is seeking a Senior Math Libraries Engineer focused on emulation of math operations across precisions for AI and HPC workloads. You will design and implement high-performance numerical linear algebra software on GPUs, spanning diverse applications from NLP to scientific simulations.

The role combines technical leadership with collaboration across product teams to optimize libraries and guide architectural choices.

Qualifications

• PhD or Master’s degree in Computer Science, Applied Math, or related field (or equivalent experience).
• 5+ years of experience in designing, developing, testing, maintenance, and performance optimization of production software using CUDA and C++.
• Good knowledge of GPU hardware architecture and numerical methods for linear algebra.
• Strong teamwork, communication, and documentation habits.

Responsibilities

• Scoping, designing, and implementing high quality and performance numerical dense linear algebra software on GPUs.
• Providing technical leadership and feedback to library engineers, and mentoring interns.
• Working closely with product management and other customers to define feature and performance roadmaps.
• Finding opportunities to improve library performance and reduce maintenance overhead through re-architecting.

Skills

CUDA programming

C++ development

Numerical methods

GPU architecture understanding

Python scripting

Education

Master’s degree in CS/Applied Math

PhD in CS/Applied Math (preferred)

Tools

CUTLASS

Assembly for performance

Python

CUDA toolchain

Job description

NVIDIA Corporation is seeking a Senior Math Libraries Engineer focused on emulation of math operations across precisions for AI and HPC workloads. You will design and implement high-performance numerical linear algebra software on GPUs, spanning diverse applications from NLP to scientific simulations.

The role combines technical leadership with collaboration across product teams to optimize libraries and guide architectural choices.