Math Device Extension Libraries Intern - 2027
nvidia.wd5.myworkdayjobs.com
- Job written in
- English
- Location
- Zürich
- Work type
- Hybrid
- Type
- Full-time
NVIDIA is seeking software engineering interns to expand its Device eXtension (Dx) APIs for its GPU‑accelerated math libraries. The company's accelerated computing platform underpins high‑performance computing and AI workloads across many sectors, from scientific research to autonomous systems. Interns will join the libraries team that builds and optimizes the core mathematical functions powering these applications. The day‑to‑day work involves prototyping and implementing numerical algorithms for Dx libraries such as cuBLASDx, cuSolverDx, cuFFTDx, cuRANDDx, nvCOMPDx, NPPDx or libmathdx on the latest NVIDIA GPUs. Interns will analyze GPU performance, identify optimization opportunities, and collaborate with senior engineers to understand use cases and requirements. Additional tasks include building tooling to translate library APIs into LLM‑friendly formats and contributing to general software engineering activities that improve the developer experience. Candidates must be pursuing an MS or PhD in Computer Science, Artificial Intelligence, Applied Mathematics, or a related discipline. They need strong C++ coding abilities, including debugging, performance analysis, and test development. Experience with parallel or GPU programming, using CUDA, OpenMP, OpenCL, SYCL, or similar frameworks, is required, as is familiarity with linear algebra, FFT, or data‑compression algorithms. Effective collaboration, clear communication, and solid documentation habits are also essential. Preferred qualifications include knowledge of composability, fusions, and compiler technologies, as well as an understanding of GPU and network hardware architectures. Familiarity with Python and recent CUDA innovations such as cuTile and CUDA Tile C++ is advantageous. Prior involvement in AI‑assisted software development, experience with large language models, MCP, RAGs, or agentic tooling, and exposure to numerical methods, floating‑point arithmetic, and error analysis are considered nice‑to‑have. The internship offers mentorship from senior engineers, exposure to cutting‑edge hardware, and the chance to influence widely used mathematical libraries. What the role asks for: - Pursuing MS or PhD in CS, AI, Applied Mathematics or related field - Strong C++ programming, debugging, performance analysis, test building - Parallel or GPU programming experience with CUDA, OpenMP, OpenCL, SYCL or similar - Experience with linear algebra or FFT or data‑compression algorithms - Collaboration, communication, and documentation habits - Nice-to-have: understanding of composability and fusions, compilers, language implementation - Nice-to-have: knowledge of GPU and network hardware architecture - Nice-to-have: familiarity with Python and recent CUDA developments like cuTile - Nice-to-have: prior work in AI‑assisted software development, LLMs, MCP, RAGs or agenting tooling - Nice-to-have: exposure to numerical methods, floating‑point arithmetic, numerical error analysis
Lebenslauf-Vorlage für deine Bewerbung
Für diesen Titel gibt es keine eigene Vorlage — aber über 190 nach Beruf, alle im Schweizer Aufbau mit Beispieltext. Nimm die, die deiner Stelle am nächsten kommt.
Lebenslauf-Vorlage Schweiz ansehenWas sonst gerade in Zürich offen ist
| offene Inserate | 8'947 |
|---|---|
| neu in den letzten 7 Tagen | 1'370 |
| als Teilzeit ausgeschrieben | 333 |
| auf Deutsch · der sprachlich erfassten Inserate | 69% |
| auf Französisch · der sprachlich erfassten Inserate | 1% |
| auf Englisch · der sprachlich erfassten Inserate | 30% |
| auf Italienisch · der sprachlich erfassten Inserate | 0% |
Stand 22. November 2026.
Weitersuchen
- Alle Jobs in Zürich
- Lebenslauf mit KI erstellen
- ATS-Lebenslauf prüfen
- Bewerbungsschreiben für dieses Inserat