Description

Required Skills & Experience:

• Strong understanding of modern machine learning techniques and toolsets
• Experience debugging and optimizing ML training performance end-to-end
• Deep knowledge of GPU architecture, including PTX, SASS, warps, cooperative groups, Tensor Cores, and GPU memory hierarchy
• Hands-on debugging and optimization experience with CUDA GDB, NVIDIA Nsight Systems, and Nsight Compute
• Experience with GPU libraries such as Triton, CUTLASS, CUB, Thrust, cuDNN, and cuBLAS
• Strong understanding of CUDA graph launches, Tensor Core arithmetic, warp-level synchronization, asynchronous memory operations, latency, and throughput optimization
• Experience with high-performance networking technologies including InfiniBand, RoCE, GPUDirect, PXN, rail optimization, and NVLink for GPU cluster communication
• Knowledge of distributed GPU training and collective communication frameworks such as NCCL and MPI

Key Skills

Education

Bachelor's degree