Senior Ascend Npu Systems Engineer

Ascend NPU systems engineering drives Huawei Canada’s foundation-model performance through AscendC kernels and distributed scaling. This is a permanent senior engineering opportunity.As a Senior System Engineer, you will develop compute operators and optimize pre-training and post-training workloads. The work spans AscendC, Triton, TileLang, MindSpeed, and upstream frameworks. You will improve training efficiency across Ascend NPU clusters through profiling, parallelism, and numerical alignment.Key Responsibilities:
Design and tune FlashAttention, GEMM, RMSNorm, and MoE operatorsOptimize MindSpeed and distributed foundation-model training pipelinesTune TP, PP, CP, EP, ZeRO, and FSDP parallelismProfile Ascend hardware and reduce compute-communication overheadContribute operators and acceleration features to open-source projectsRequirements:
Technical degree and three-plus years of relevant experienceAscendC or CUDA C/C++ operator-development experienceDistributed framework experience with MindSpeed, Megatron, FSDP, veRL, or vLLMStrong C/C++ and modern Python programming proficiencyExperience with Ascend Profiler, PyTorch Profiler, or NsightApply systems expertise in AscendC, distributed training, profiling, and low-precision computing to Huawei Canada’s accelerator platforms.
#J-18808-Ljbffr