Champion the advancement of AI by fostering innovative solutions, cultivating a thriving ecosystem, and driving strategic roadmaps for deep learning compilers. Collaborate with internal and external engineers and researchers to build product-based roadmaps, maintain relationships with open-source communities, and gather customer insights to create impactful solutions1. CUTLASS - Abstractions for implementing high-performance matrix-matrix multiplication (GEMM)https://github.com/NVIDIA/cutlass2. cuDNN - GPU-accelerated Deep Neural Network libraryhttps://developer.nvidia.com/cudnn3. NVIDIA contributions to OpenAI Triton, OpenXLA, and IREE

Worked with software developers, hardware developers, and research scientists to ensure that the math libraries meet the needs of a variety of applications.Defined and proved the market value of the product, gathered market intelligence, worked closely with engineering to set requirements and priorities, engaged with customers, presented at conferences, defined go-to-market strategies, and contributed to the creation of technical content.1. Math Libraries - (cuBLAS, cuFFT, cuSOLVER, cuSPARSE, cuRAND, cuTENSOR)https://developer.nvidia.com/gpu-accelerated-libraries2. CUTLASS - Abstractions for implementing high-performance matrix-matrix multiplication (GEMM) https://github.com/NVIDIA/cutlass3. nvCOMP - GPU Compression and Decompression https://developer.nvidia.com/nvcomp

Supported Public Sector assisting with CUDA development and optimizations, along with education and proof of concepts for customers on various NVIDIA tool sets (e.g., Math Libraries, Nsight Systems/Compute)