About this role
Founding Engineer - ML Performance at Urun. Location: San Francisco, California, United States. Role: Write CUDA kernels, Optimize inference latency, Drive performance improvements Requirements: Hands-on CUDA, GPU optimization, and large-scale model inference experience; strong systems and performance engineering skills. Category: Engineering Seniority: Senior Level Tools: CUDA, GPU, NCCL, PyTorch, Triton, TensorRT, CUDA kernels Commitment: Full Time Workplace: Remote Languages: English