Senior Math Libraries Engineer - Sparsity in AI
NVIDIA
PythonPyTorch
Senior Software Engineer, cuBLASDx and cuSolverDx
NVIDIA
full-time
Posted on:
Origin: • 🇺🇸 United States • California
Visit company websiteSalary
💰 $148,000 - $287,500 per year
Job Level
Senior
Tech Stack
PythonPyTorch
About the role
- Design modern, flexible, and easy to use APIs for math libraries and lead design reviews with collaborators
- Work closely with internal teams (engineering, Product Management) and external partners (researchers) to understand use cases and requirements
- Design, develop, and optimize GPU-accelerated math libraries (Device eXtension APIs such as cuBLASDx and cuSolverDx)
- Become a domain expert by continuously surveying current trends in software systems
- Deliver high-performance, flexible implementations for HPC and AI applications
- Collaborate across teams to ensure runtime optimization, integration with high-level languages and ecosystems
Requirements
- PhD or MSc degree in Computer Science, Applied Math, or a related science or engineering field is preferred (or equivalent experience)
- 3+ years of experience designing and developing software for high-performance computing and/or AI applications
- Advanced C++ skills, including modern design paradigms (e.g., template meta-programming, RAII)
- Parallel programming experience with CUDA or OpenCL
- Strong collaboration, communication, and documentation habits
- Experience using graph compilers and/or JIT compilation workflows (e.g. XLA, LLVM, MLIR, Numba, NVRTC) (nice to have)
- Programming skills with Python
- Experience with modern build and test automation (e.g., CMake, CI/CD, sanitizers)
- Experience with CCCL, OpenMP, OpenACC, multi-threading, MPI, PGAS (nice to have)
- Strong background in numerical methods (e.g., FFT, numerical linear algebra)
- Experience with scientific and deep learning libraries and frameworks (e.g., PyTorch, JAX, MKL, MAGMA, PETSc, Kokkos)
