Senior Software Engineer, CUTLASS Platform

What you'll do

• Develop core CUTLASS components including Tensor Core MMAs, copies, and schedulers in CUDA C++.
• Build the CUTLASS Python DSL using MLIR by designing dialects and compiler passes.
• Author example kernels to showcase novel GPU hardware features for high-performance computing.
• Provide feedback on programming models to the GPU architecture, CUDA, and NVVM/PTX compiler teams.
• Assess the performance of future GPU hardware features to improve the software stack.
• Design abstractions for Tensor Core and GPU hardware features in MLIR, Python, and C++.

What we're looking for

• Masters or PhD degree in Computer Science, Computer Engineering, or a related field (or equivalent experience).
• 3+ years of relevant industry experience.
• Strong proficiency in C++ programming and software design, including debugging, performance evaluation, and testing.
• Experience working with high-performance code generation and knowledge of compiler transformations and optimizations.
• Deep understanding of computer architecture and parallel computing programming models.
• Experience writing high-performance kernels at low levels of abstractions like NVVM/PTX for GPUs (preferred).
• Hands-on compiler design experience, particularly in MLIR (preferred).
• Understanding of deep learning models, algorithms, and frameworks (preferred).