Senior Software Engineer, CUDA Core Libraries

NVIDIA's accelerated computing platform powers modern HPC and AI. The role focuses on CUDA Core Libraries, C++ and Python libraries enabling GPU-accelerated software development, including projects such as CCCL (Thrust, CUB, libcudacxx), cuda-python, and numba-cuda.

• BS, MS, or PhD in Computer Science, Computer Engineering, or related field, or equivalent experience.
• At least 8 years of related development experience.
• Strong programming skills in C++, Python, or both, with interest in systems-level software.
• Solid understanding of modern C++ (templates, generics, standard library) and/or Python library development and packaging.
• Practical experience with parallel or heterogeneous programming (CUDA, OpenMP, GPU-accelerated Python).
• Experience contributing to production software or open-source libraries including testing, profiling, and code review.
• Ability to work independently and drive projects to completion.
• Clear written communication skills for technical design and documentation.
• Comfort navigating large multi-language codebases (C++, Python, CMake, Pixi, CI systems).

Nice to have:

• Strong understanding of CPU/GPU architecture and hardware performance implications.
• Experience with CUDA C++, CUDA Python, PyTorch, JAX, Numba, CuPy, or similar GPU-accelerated stacks.
• Familiarity with Thrust, CUB, libcudacxx, or other modern C++/GPU libraries.
• Experience with compiler infrastructure or tooling (LLVM, Clang tooling, MLIR).
• Interest in developer tools, library design, and improving developer productivity.

• Develop and implement CUDA Core Libraries in C++ and/or Python, including parallel algorithms and idiomatic language bindings.
• Compose, optimize, and evolve GPU algorithms and APIs, covering high-level interfaces and low-level performance tuning.
• Own features end-to-end: development, implementation, testing, benchmarking, documentation, and maintenance.
• Improve developer experience with CI, tests, benchmarks, packaging, examples, and documentation.
• Collaborate with senior CUDA engineers through design reviews, code reviews, and open-source workflows.
• Engage with users on issues, performance investigations, and API feedback.