GPGPU Software Architect/ Principal Engineer

XPENG, a leading smart technology company, is seeking a GPGPU Software Architect/Principal Engineer to lead the development of a CUDA-compatible software stack for their next-generation GPUs. This role involves developing a 3-year roadmap, designing a modular runtime architecture, ensuring compatibility with CUDA 12.x, and building an observability platform to optimize performance and identify bottlenecks. The company focuses on integrating AI and autonomous driving technologies into electric vehicles and eVTOL aircraft.

Requirements

• 10 years + in systems software, with at least 5 years in designing CUDA Compute stacks
• Led end-to-end development of a GPU Runtime or AI acceleration library generation
• Comprehensive mastery of PTX/SASS, CUDA Driver API, and cuBLAS/cuDNN internals; experience with LLVM NVPTX backend
• Profound understanding of GPU micro-architecture, including SM architecture, Warp Scheduler, Shared-Memory conflicts, and Tensor Core pipelines
• Proficiency with PCIe/CXL/RDMA topologies, NUMA settings, and GPU Direct RDMA/Storage

Benefits

• Bonus
• Equity
• Benefits