Math Device Extension Libraries Intern - 2027
NVIDIAJob Title
Math Device Extension Libraries Intern - 2027
Role Summary
As an intern on the Math Device Extension Libraries team, you will work with senior engineers to design, implement, and optimize GPU-accelerated numerical algorithms and APIs for NVIDIA's math libraries. The team delivers high-performance implementations and integrates them with modern language ecosystems and developer workflows.
Projects include algorithm development, performance tuning on NVIDIA GPUs, API design, and tooling to improve library usability.
Experience Level
Entry-level (Internship). Intended for students or early-career engineers; specific years of experience are not provided.
Responsibilities
Primary responsibilities include:
- Prototype and implement numerical algorithms for Device eXtension (Dx) math libraries (e.g., cuBLASDx, cuSolverDx, cuFFTDx, cuRANDDx, nvCOMPDx, NPPDx, libmathdx).
- Analyze GPU implementation performance and identify opportunities for improvement.
- Collaborate with team members to gather use cases and refine API designs.
- Develop performance optimizations targeting recent NVIDIA GPUs.
- Prototype tooling to represent math-library APIs in LLM-friendly formats and improve developer workflows.
Requirements
Must-have skills and experience:
- 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, FFTs, or data compression algorithms.
- Good collaboration, communication, and documentation habits.
Nice-to-have:
- Understanding of composability, fusion techniques, compilers, or language implementation.
- Familiarity with GPU and network hardware architecture.
- Experience with Python and recent CUDA developments (e.g., cuTile, CUDA Tile C++).
- Prior work with AI-assisted software development, LLMs, RAGs, or agenting tooling.
- Exposure to numerical methods, floating-point arithmetic, and numerical error analysis.
Education Requirements
Pursuing an MS or PhD in Computer Science, Artificial Intelligence, Applied Mathematics, or a related technical field (graduate-student internship).
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
