We are now looking for a Senior AI Frameworks Engineer (C++/Python)! NVIDIA's high-performance computing platforms are powering the AI revolution across many applications and industries. Within our software stack, CUTLASS stands out as a popular open-source ecosystem dedicated to high-performance math primitives. Since 2017, it has provided the community with C++ template abstractions to implement custom GEMM and related computations efficiently on NVIDIA GPUs. We are building the next frontier of this ecosystem: Pythonic CUTLASS (CUTLASS DSL). This initiative aims to bring 'speed-of-light' performance and powerful abstractions of our stack directly into the Python environment. Join the CUTLASS team and help bridge the gap between low-level hardware primitives and high-level developer productivity. If you are passionate about building elegant, high-performance DSLs and want to empower the next generation of AI researchers and engineers with better tools, apply today!

As a core contributor to the CUTLASS project, you will use your expertise in systems programming and API design to create a world-class developer experience for GPU programming and kernel delivery.

Design APIs that prioritize user productivity, providing a 'native' feel for developers accustomed to modern scientific computing and deep learning frameworks.

Develop robust compilation infrastructure—including AST transformations and JIT-friendly execution—to lower Pythonic descriptions into high-performance GPU machine code.

Optimize developer experience by creating debugging tools, profiler integrations, and validation methodologies that make writing and using kernels easy.

Build production-grade delivery infrastructure for the open-source community, managing everything from package distribution (wheels, conda) to the user-facing documentation and testing.