Senior Software Engineer, CUTLASS Platform
NVIDIAJob Title
Senior Software Engineer, CUTLASS Platform
Role Summary
Join the CUTLASS team to design and implement low-level GPU software components and compiler support that enable high-performance linear algebra and Tensor Core primitives on NVIDIA GPUs. The role focuses on CUDA C++, a CUTLASS Python DSL, and MLIR-based compiler work to produce efficient kernels and demonstrate novel hardware features.
Experience Level
Senior. Typical expectation: 3+ years of relevant industry experience.
Responsibilities
The role combines systems programming, compiler design, and collaboration with GPU architecture and compiler teams. Key responsibilities include:
- Develop core CUTLASS platform components: Tensor Core MMAs, copies, synchronization primitives, schedulers, and related CUDA C++ code and Python DSL constructs.
- Design MLIR dialects and compiler passes for the CUTLASS Python DSL and advance the MLIR-based backend.
- Author example kernels and reference implementations that exercise CUTLASS abstractions and new GPU features to validate performance.
- Work with GPU architecture, CUDA, and compiler teams to evaluate programming models and assess performance of current and future hardware features.
- Debug, profile, and test performance-critical code; contribute to performance evaluations and benchmarking.
Requirements
Must-have technical skills and experience:
- 3+ years of relevant industry experience in systems, compilers, or high-performance software development.
- Strong C++ programming and software design skills, including debugging, performance evaluation, and testing.
- Experience with high-performance code generation and knowledge of compiler transformations and optimizations.
- Deep understanding of computer architecture and parallel computing programming models.
Nice-to-have:
- Experience writing low-level high-performance kernels (NVVM/PTX or equivalent).
- Hands-on compiler design experience, particularly with MLIR.
- Familiarity with deep learning models, algorithms, and frameworks.
Education Requirements
Master's or PhD in Computer Science, Computer Engineering, or a related field — or equivalent practical experience.
About the Company
Company: NVIDIA
Headquarters: Santa Clara, California, USA
NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.
