Live opening · Posting date unavailable

企业微信-大模型训练框架开发工程师-AI Infra(成都/北京)

Tencent · Guangzhou, China
Own > 3 years of working experience

At a glance

The key details from the original listing.

Posting date unavailable
CompanyTencent
LocationGuangzhou, China
Experience> 3 years of working experience
SkillsC++, PyTorch
SourceOwn
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

Get JobBeeper Mobile App

Never miss a job opening! Get instant job alerts on your phone.

Subscribers see fresh openings within minutes. Download the JobBeeper App on Google Play to get real-time push notifications and apply before anyone else.

⚡ Instant Push Alerts 🎯 Tailored Filters 🚀 Direct Employer Links
GET IT ON Google Play

More openings worth a look

Recently tracked roles with full details and direct application links.

6 roles
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 →
⚡ Get fresh job alerts 📱 Get App