Note: The job is a remote job and is open to candidates in USA. NVIDIA’s GPU Architecture Group is looking for architects to contribute to the design of their proprietary profiler subsystem embedded in every GPU. The role involves combining skills in hardware modeling and verification with an understanding of GPU architecture to innovate methods of hardware profiling for performance optimization.
Responsibilities
- Architect and plan features in concert with software, hardware, and verification teams working across the globe to implement next generation GPU profiling features
- Build functional and performance models to refine and verify hardware designs
- Create test plans to validate the features you design and contribute to their implementation
- Constantly develop your skills for practical innovation by improving your understanding of the AI workloads, the GPU architecture, and the profiling software stack
Skills
- Masters, or PhD in relevant field (Eg: Computer Science, Computer Engineering or Electrical Engineering) or equivalent experience
- 3+ years of relevant computer architecture, ASIC design/verification, or software development experience
- Strong programming skills in C++ (or similar) and Python (or similar)
- Solid foundation in computer architecture and hardware performance analysis
- Experience with performance modeling and hardware simulation, ideally using SystemC
- Strong communication and interpersonal skills including the ability to work with a distributed interdisciplinary team
- Expertise in developing and optimizing parallel algorithms, particularly using GPUs
- Extensive experience as a user or developer of CPU or GPU profiling tools
- Background with AI and/or high-performance computing applications
- Experience contributing to and debugging large codebases with many developers
Benefits
- You will also be eligible for equity and [benefits](https://www.nvidia.com/en-us/benefits/).
Company Overview
Company H1B Sponsorship