[Skip to main content](#main-content)

[OpenNash Jobs](https://jobs.opennash.com/)
[Hiring report](/reports/hiring/) · [All Kuaishou Technology jobs](https://jobs.opennash.com/companies/kuaishou-technology/) · [Search jobs](/search/)

Kuaishou Technology · Beijing, Hangzhou

# 大模型训练平台研发实习生

Beijing, Hangzhou 

Listed on Kuaishou Technology’s official careers site. Listed as of October 19, 2026. Check that it is still open and apply there.
[Apply on Kuaishou Technology’s careers site →](https://zhaopin.kuaishou.cn/#/official/social/job-info/29674)

[OpenNash Jobs](https://jobs.opennash.com/) / [Kuaishou Technology](https://jobs.opennash.com/companies/kuaishou-technology/) / 大模型训练平台研发实习生

## Job description

### 核心平台建设
- 设计和研发支撑大规模分布式训练的基础设施平台，负责GPU集群的资源调度、生命周期管理及作业编排，提升资源利用率和训练效率；

### 稳定性与容错
- 构建自动故障感知、故障自愈与断点续训（Checkpoint 保存与恢复）机制，保障大规模训练的长稳运行，提升训练有效时间占比（MTBF/MTTR优化）；

### 可观测性
- 建设面向大模型训练的全方位可观测体系，采集和分析硬件（GPU、RoCE/IB网络）、存储及训练框架的性能指标，快速定位慢节点或故障点，实现训练状态透明化；

### 性能优化
- 结合训练框架（如 Megatron-LM、DeepSpeed）进行内核级优化，优化网络通信拓扑（如 NCCL）及存储I/O流水线，降低训练成本，提升模型训练吞吐；

### 资源效率
- 设计高效的集群混部和碎片资源利用方案，平衡多租户隔离与资源利用率，支持潮汐调度和弹性训练。

### 编程能力
- 扎实的编程功底，熟练使用 Python/Go/C++ 中的至少两种，具备高性能网络编程或系统级开发经验，能独立完成大型模块的设计与开发；

### 分布式系统
- 熟悉 Kubernetes 底层原理及 Operator 开发模式，有自定义调度器、控制器开发经验者优先；熟悉资源调度系统（Yarn/Slurm/K8s）架构及实现；

### AI基础设施
- 了解常用AI框架（PyTorch）的分布式训练原理，熟悉 NCCL/RDMA 等通信库；对 GPU 架构（NVIDIA A100/H800等）有较深理解，有 CUDA 开发或性能剖析（Profiling）经验者加分；

### 网络与存储
- 了解分布式存储（如 Ceph、Lustre、JuiceFS、Alluxio）在大模型训练场景的适配与调优；熟悉高性能网络（RoCE/InfiniBand）原理及常见问题排查；

### 故障排查
- 具备极强的系统问题排查能力，能处理从内核、驱动、库到应用层的系统性故障，有大型集群稳定性保障经验。

### 加分项
- 有万卡规模 GPU 集群运维或建设经验；
- 对 PyTorch 源码有深入研究，或向社区提交过 Patch；
- 熟悉 Megatron-LM、DeepSpeed 源码，了解 3D 并行策略及实现；
- 熟悉 GPU 虚拟化、容器化技术（如 vGPU、CUDA MPS）及算力隔离方案。

## At a glance
- Posted by the employer: Not stated
- First seen by OpenNash: Oct 19, 2026
- Last checked: Oct 19, 2026
- Listed for: Under a day
- Location: Beijing, Hangzhou[Apply on Kuaishou Technology’s careers site →](https://zhaopin.kuaishou.cn/#/official/social/job-info/29674)

## More jobs at Kuaishou Technology

### [AI安全专家](https://jobs.opennash.com/companies/kuaishou-technology/jobs/41b810ad789fb68572e0/)

Beijing, Hangzhou

### [AI应用开发实习生（研发效能方向）-【商业化】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/898df3b56907cce1f883/)

Beijing, Hangzhou

### [AI应用研发工程师（品牌广告）-【商业化】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/f073b7c92012a83a64cf/)

Beijing, Hangzhou

### [AI应用研发工程师（效果广告）-【商业化】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/2da22855636c2ff7c95e/)

Beijing, Hangzhou

### [Hrbp-【电商】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/72cddff94c16fc19abaf/)

Beijing, Hangzhou

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/)