GPU Math Libraries Intern: Optimize High-Performance DX APIs

NVIDIA Corporation; Województwo mazowieckie; On-site; PLN 118,000 - 204,000; Full time

Job summary

NVIDIA Corporation in Poland offers software engineering internships to help expand our Dx API catalog for math libraries on NVIDIA GPUs. You will work with senior engineers to design, implement, and optimize numerical algorithms and APIs across cuBLASDx, cuSolverDx, cuFFTDx, cuRANDDx, nvCOMPDx, NPPDx and libmathdx.

You will analyze GPU performance, collaborate to understand use cases, and prototype tooling to expose APIs to LLM-friendly representations.

Qualifications

• Pursuing a MS or PhD degree in Computer Science, Artificial Intelligence, Applied Mathematics, or related field
• Strong C++ programming, debugging, performance analysis, and test building skills
• Parallel or GPU programming experience using CUDA, OpenMP, OpenCL, SYCL or similar
• Experience with linear algebra or FFT or data compression algorithms
• Collaboration, communication, and documentation habits.

Responsibilities

• Prototype and develop numerical algorithms for high-performance math device extension libraries: cuBLASDx, cuSolverDx, cuFFTDx, cuRANDDx, nvCOMPDx, NPPDx or libmathdx on ground breaking NVIDIA graphics processors.
• Analyze the performance of GPU implementations and find opportunities for improvements
• Collaborate with team members to understand software use cases and requirements
• Prototype tooling and solutions to help transform math libraries’ APIs into LLM-friendly representations across popular codegen tools.

Skills

C++ programming

Performance analysis

Debugging

Test building

GPU programming

Education

MS or PhD in Computer Science or related field

Tools

CUDA

OpenMP

OpenCL

SYCL

Job description

NVIDIA Corporation in Poland offers software engineering internships to help expand our Dx API catalog for math libraries on NVIDIA GPUs. You will work with senior engineers to design, implement, and optimize numerical algorithms and APIs across cuBLASDx, cuSolverDx, cuFFTDx, cuRANDDx, nvCOMPDx, NPPDx and libmathdx.

You will analyze GPU performance, collaborate to understand use cases, and prototype tooling to expose APIs to LLM-friendly representations.