Founding GPU Engineer - CUDA Performance for HPC

Fuse Energy, LLC seeks an experienced CUDA performance engineer to design, optimize, and deploy high-throughput CUDA kernels across multi-GPU systems. You will profile hardware bottlenecks, develop tooling to monitor energy usage, and collaborate with ML engineers to integrate kernels into scalable training and inference pipelines.

The role requires deep GPU architecture knowledge, strong C++/CUDA skills, and experience with Nsight, NCCL, and MPI.