qubitsok.com

Cut Noise. Work Quantum.

About Jobs Salaries Latest Papers Post a Job Sign In

Back to Job Listings

Europe, Poland, Warsaw

•

Posted 27 days ago

CUDA Math Libraries Intern - 2026

🏢 NVIDIA

•

PLN 52 - 91 per hour

AI Summarised

Visit Website

Role Type

🛠️ Engineer / Developer

Role Focus

💻 Code Systems

Seniority

🌱 Internship / Entry-Level

🌸 PhD / Postdoc

Employer Type

🏢 Industry

This internship at NVIDIA focuses on developing accelerated mathematical and data processing libraries integral to high-performance computing and deep learning, including foundational primitives for quantum computing. The intern will collaborate with senior engineers to extend existing libraries and build new ones, implementing new algorithms, defining APIs, and analyzing performance. The main purpose of the role is to deliver state-of-the-art functionality and performance improvements for these critical software components.

Key Responsibilities

Collaborate with team members to accurately understand software requirements and intended use cases.

Analyze the performance of current GPU or CPU implementations to identify and execute opportunities for improvement.

Prototype and develop new algorithms suitable for single node and multi GPU cluster environments.

Define new Application Programming Interfaces (APIs) for library functionalities.

Find and implement appropriate solutions for difficult numerical corner cases within the mathematical libraries.

Required Skills

Studying towards a Master's (MS) or PhD degree in Computational Science, Computer Science, Applied Mathematics, Engineering, or a related field.

Programming proficiency in C/C++ and Python.

Experience with parallel or GPU programming (AVX, NEON, OpenMP, MPI, SHMEM, CUDA, or OpenCL).

Nice-to-have Skills

Exposure to floating-point arithmetic and numerical error analysis.

Knowledge of GPU, CPU, and network hardware architecture.

Understanding of composability, fusions, compilers, and implementation of programming languages.

Experience implementing sparse or dense linear algebra algorithms.

Experience with domain-specific language design and compiler optimizations, especially sparse compilers (MLIR or TACO).

Technology Tags

High-Performance Computing

The libraries developed are a key part of high-performance computing software stacks.

Linear algebra

The job focuses on developing libraries that provide primitives for dense and sparse linear algebra.

Classical programming

Strong programming skills in C/C++ and Python are required for implementing algorithms and defining APIs.

GPU-Quantum Interfaces

The position involves developing libraries used for quantum computing on NVIDIA platforms.

Quantum compilers

The role involves experience with domain-specific language design and compiler optimizations, including sparse compilers like MLIR or TACO.

Benchmarking

A core responsibility is analyzing the performance of GPU/CPU implementations to find improvements.

Optimisation

The job involves analyzing performance, finding improvements, and developing algorithms crucial for optimization problems across various fields.

Source Job Description

NVIDIA is looking for software engineering interns for our teams which develop accelerated mathematical and data processing libraries like cuSparse, cuBLAS, cuSOLVER, cuFFT, nvImgCodec, nvComp, nvmath-python or DALI, that are a key part of high-performance computing and deep learning software stacks. The main purpose of these libraries is to provide the fastest primitives for linear algebra (dense and sparse), quantum computing and computer vision. Does the idea of being at the heart of these projects and applying your knowledge to make an impact around world sound exciting? If yes, then come and join our team!

In this role you will be part of our team responsible for the development of libraries that provide groundbreaking functionality and performance. The internship may include extending the capabilities of existing as well as building new libraries that will be used in various AI and HPC applications. It will involve working with senior software engineers who will provide mentorship and guidance. The project will include implementing new algorithms, defining APIs, analyzing performance, finding appropriate solutions for difficult numerical corner cases, and other general software engineering work.

What You’ll Be Doing

Collaborate with team members to understand software use cases and requirements
Analyze the performance of GPU or CPU implementations and find opportunities for improvements
Prototype and develop algorithms for single node and multi GPU clusters

What We Need To See

Studying towards a MS or PhD degree in Computational Science, Computer Science, Applied Mathematics, Engineering, or a related field.
Programming skills (C/C++, Python)
Parallel or GPU programming experience (AVX, NEON, OpenMP, MPI, SHMEM, CUDA or OpenCL)

Ways To Stand Out From The Crowd

Exposure to floating-point arithmetic and numerical error analysis.
Knowledge of GPU/CPU and network hardware architecture.
Understanding of composability and fusions, compilers, and implementation of programming languages
Experience implementing sparse or dense linear algebra algorithms.
Experience with domain-specific language design and compiler optimizations, in particular sparse compilers (MLIR or TACO)

NVIDIA is widely considered to be one of the technology world's most desirable employers. We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative, autonomous, and love a challenge, we want to hear from you!

Our internship hourly rates are a standard pay based on the position, your location, year in school, degree, and experience. For Poland: the hourly rate for our interns is 52 PLN - 91 PLN.

JR2007027