About this role
HPC Engineer at AlphaGrep Securities. Location: Shanghai, Shanghai, China. Role: operating clusters, optimizing performance, troubleshooting networks Requirements: Experience operating large-scale GPU/HPC clusters, RDMA programming and debugging (libibverbs), InfiniBand/RoCEv2, GPUDirect, NCCL, Slurm, high-performance filesystems, strong Linux administration, and scripting in Python/Bash; C/C++ preferred. Category: Engineering Seniority: Senior Level Tools: RDMA verbs, libibverbs, GPUDirect RDMA, GPUDirect Storage, NCCL, CUDA, CUDA drivers, OFED, InfiniBand, RoCEv2, Slurm, Lustre, BeeGFS, WEKA, VAST, DDN/ExaScaler, Python, Bash, C++, Linux Commitment: Full Time Workplace: Onsite Languages: English