[Skip to main content](#main-content) [OpenNash Jobs](https://jobs.opennash.com/) [Hiring report](/reports/hiring/) · [All Tencent Holdings jobs](https://jobs.opennash.com/companies/tencent-holdings/) · [Search jobs](/search/) Tencent Holdings · Guangzhou # 企业微信-大模型训练框架开发工程师-AI Infra（成都/北京） Guangzhou Listed on Tencent Holdings’s official careers site. Listed as of October 19, 2026. Check that it is still open and apply there. [Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=1976128424510644224) [OpenNash Jobs](https://jobs.opennash.com/) / [Tencent Holdings](https://jobs.opennash.com/companies/tencent-holdings/) / 企业微信-大模型训练框架开发工程师-AI Infra（成都/北京） ## Job description ### Responsibilities - 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； - 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； - 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； - 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； - 负责 PyTorch、TensorRT-LLM、vLLM、SGLang、Megatron-LM 等框架下的大模型性能优化落地； - 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。 Requirements - 熟悉 C/C++、CUDA 或 Triton 编程，有 GPU 算子开发或性能优化经验； - 熟悉 NVIDIA GPU 架构，理解 SM、Warp、Tensor Core、Shared Memory、Memory Coalescing、Occupancy 等概念； - 熟悉大模型训练或推理流程，了解 Attention、GEMM、MoE、KV Cache、并行策略等核心模块； - 熟悉分布式训练/推理优化，理解 TP、PP、DP、EP、NCCL、RDMA 等技术； - 有实际 profiling 和性能调优经验，能够通过工具定位瓶颈并给出优化方案； - 有 NVIDIA GPU 或 国产加速卡 实际优化经验者优先； - 不要求候选人覆盖 AI 全栈所有方向，只要在大模型训练/推理、GPU 算子优化、分布式通信、性能调优、推理框架等任一方向有较深入理解和实践经验，均欢迎投递。 ## At a glance - Posted by the employer: Not stated - First seen by OpenNash: Jul 19, 2026 - Last checked: Oct 19, 2026 - Listed for: 92 days - Location: Guangzhou[Apply on Tencent Holdings’s careers site →](https://careers.tencent.com/en-us/jobdesc.html?postId=1976128424510644224) ## More jobs at Tencent Holdings ### [《逆战：未来》-关卡策划](https://jobs.opennash.com/companies/tencent-holdings/jobs/3fd6daca74f05f339c14/) Guangzhou ### [企业微信-AI Agent Harness 全栈工程师-（成都）](https://jobs.opennash.com/companies/tencent-holdings/jobs/b25acf36158f5448bdfd/) Guangzhou ### [企业微信-AI产品经理-微信互通方向](https://jobs.opennash.com/companies/tencent-holdings/jobs/f5c8e376f2d87fe5aa9a/) Guangzhou ### [企业微信-AI产品经理-效率办公 AI](https://jobs.opennash.com/companies/tencent-holdings/jobs/504e9a531b2cc6c30245/) Guangzhou ### [企业微信-AI产品经理-智能助理Agent](https://jobs.opennash.com/companies/tencent-holdings/jobs/8464e085c5a447646f31/) Guangzhou ## Similar jobs at other companies ### [AI基建-大模型训练框架开发工程师](https://jobs.opennash.com/companies/xiaomi/jobs/d2f137425fc34b2dcae5/) Xiaomi · 北京 ### [大模型训练框架开发工程师](https://jobs.opennash.com/companies/xiaomi/jobs/b6af0109bba8a365e5cd/) Xiaomi · 北京 ### [Servicetechnicus Infra](https://jobs.opennash.com/companies/bouygues/jobs/1171d5fcafc8a2e1c25c/) Bouygues · ARNHEM, Netherlands ### [Cloud Infra Engineer](https://jobs.opennash.com/companies/grasim-industries/jobs/0b92dbe21b145c95e144/) Grasim Industries · Maharashtra ### [Projectleider Ondergrondse Infra](https://jobs.opennash.com/companies/sgs/jobs/3b1ae1b162bdce2b5fa3/) SGS · Waardenburg, GE, Netherlands OpenNash lists jobs from employers’ own careers sites and does not handle applications. Dates come from the employer where stated; “first seen” and “last checked” are our own observations. OpenNash Jobs · Official listings with dates and links to the employer. [Weekly hiring report](/reports/hiring/) · [Methodology](/methodology/)