Live opening · Posting date unavailable
Tencent · Guangzhou, China
At a glance
The key details from the original listing.
CompanyTencent
LocationGuangzhou, China
Experience> 3 years of working experience
SkillsC++, PyTorch
Source
Own
ListedPosting date unavailable
About the role
Description supplied by the original job listing.
1.负责大模型训练/推理场景下的性能分析与优化,重点优化 NVIDIA GPU 及 国产芯片 的计算、显存、通信和调度瓶颈;
2.负责 CUDA / Triton / C++ 高性能算子开发与优化,包括 GEMM、Attention、MoE、KV Cache、通信融合等方向;
3.负责多卡、多机训练/推理性能调优,优化 NCCL、NVLink、NVSwitch、InfiniBand/RDMA 等通信链路;
4.负责基于 NVIDIA GPU 和 国产芯加速卡 的性能调优,提升 GPU 利用率、吞吐、延迟和显存效率;
5.负责 PyTorch、TensorRT-LLM、vLLM、SGLang、Megatron-LM 等框架下的大模型性能优化落地;
6.结合 Nsight Systems、Nsight Compute、CUDA Profiler 等工具进行性能分析,定位并解决性能瓶颈。
Experience
> 3 years of working experience
More openings worth a look
Recently tracked roles with full details and direct application links.
Good roles move before most people even see them.
Tell JobBeeper what you want and get fresh matches delivered in minutes.
Start your free trial →