Software Engineer, Kernels/CUDA (C++)
Core
Design, build, and optimize large GPU clusters and low-level CUDA kernels for demanding AI training and inference workloads.
Role type
Senior IC systems engineer (GPU kernels & clusters)
Builds
High-performance AI supercomputers and distributed computing infrastructure
Domain
AI infrastructure / High-performance computing
Deliverable
production ML models
Required skills
C++, CUDA, PTX, SASS, CUTLASS, Nsight profiling, GeMM optimization, Tensor Core optimization, multi-GPU operations, memory-bound optimization, compute-bound optimization
Preferred skills
Experience with large-scale GPU clusters, production distributed-computing infrastructure, AI research collaboration
Technologies
CUDA, C++, SASS, CUTLASS, Nsight, Linux, Fabric
Responsibilities
Develop and tune low-level CUDA kernels including GeMM and attention kernels; Profile and debug performance bottlenecks in GPU memory, networking, filesystems, and multi-GPU operations; Work with AI research teams to deliver production-ready performance and scalability
Seniority
Mid-level, hands-on IC
