Sr. Software Engineer, Kernels/CUDA (C++)
Core
Design, build, and optimize massive GPU clusters and low-level CUDA kernels for extreme-scale AI training and inference workloads.
Role type
Senior IC systems engineer (GPU kernels & compute infrastructure)
Builds
Raw GPU supercomputers and the platform layer running on top of them
Domain
AI infrastructure / High-performance computing
Deliverable
production ML models
Required skills
Low-level system programming (C/C++), CUDA kernel development, GPU memory hierarchy optimization, Linux kernel internals, Distributed compute orchestration, Multi-GPU operation, Nsight profiling, CUTLASS framework usage
Preferred skills
PTX/SASS assembly programming, Large-scale GPU cluster management, Custom kernel optimization, Memory-bound and compute-bound scenario optimization
Technologies
CUDA, CUTLASS, Nsight, Linux, Tensor Cores, GeMM, Attention mechanisms
Responsibilities
Design and optimize massive GPU clusters for training and inference; Develop and tune low-level CUDA kernels; Profile and debug bottlenecks across GPU memory, networking, and filesystems; Collaborate with AI research teams to deliver scalable performance
Seniority
Senior, hands-on IC
