[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, Shenzhen, Hangzhou

# 大模型训推优化实习岗

Beijing, Shenzhen, 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/27144)

[OpenNash Jobs](https://jobs.opennash.com/) / [Kuaishou Technology](https://jobs.opennash.com/companies/kuaishou-technology/) / 大模型训推优化实习岗

## Job description
- 负责文生图、文生视频等自研大模型核心算子的自研开发与性能优化，基于CUDA、OpenAI Triton等工具实现高性能计算加速；
- 针对AI Infra大模型推理与训练场景，优化混合精度量化策略，设计低比特计算、稀疏化压缩等方案，提升模型部署效率；
- 深入GPU/Tensor Core硬件架构，优化显存管理、计算图调度及分布式通信，提升模型训练吞吐与资源利用率；
- 搭建端到端模型推理流水线，探索多模态生成任务下的算子融合、动态编译等创新优化手段；
- 协同算法团队完成模型轻量化落地，提供量化感知训练（QAT）、模型剪枝等技术支持。
- 计算机科学、电子工程或相关专业硕士及以上学历，2年以上CUDA/GPU高性能计算开发经验；
- 精通PyTorch/Sglang/vLLM等框架底层实现，熟悉大模型部署与推理优化原理；
- 熟练掌握OpenAI Triton编程，具备算子内核开发经验（如矩阵乘、Attention、Conv等模块优化）；
- 熟悉模型量化技术（INT8/FP8/INT4混合精度）优先；
- 对GPU硬件架构（如Hopper/Ada）有深入理解，能结合硬件特性设计高性能算子。

### 加分项
- 在CVPR/NeurIPS等顶会发表过模型压缩、加速相关论文或开源项目贡献者；
- 有文生视频、3D生成等长序列生成模型的并行化优化经验；
- 熟悉分布式训练框架（DeepSpeed/Megatron）或AI芯片（如NPU）开发经验；
- 具备多模态大模型（如Diffusion Model）端到端部署落地经验。

## 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, Shenzhen, Hangzhou[Apply on Kuaishou Technology’s careers site →](https://zhaopin.kuaishou.cn/#/official/social/job-info/27144)

## More jobs at Kuaishou Technology

### [Elasticsearch 研发工程师](https://jobs.opennash.com/companies/kuaishou-technology/jobs/a2c4dd8dcfc08aa9fe66/)

Beijing, Shenzhen, Hangzhou

### [分布式图数据库研发工程师](https://jobs.opennash.com/companies/kuaishou-technology/jobs/7d45834281ca65f9e6dc/)

Beijing, Shenzhen, Hangzhou

### [分布式数据库研发工程师](https://jobs.opennash.com/companies/kuaishou-technology/jobs/90d9eeff272a3d7edd1f/)

Beijing, Shenzhen, Hangzhou

### [数据库研发工程师-【KV方向】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/943cbba3708296a77b51/)

Beijing, Shenzhen, Hangzhou

### [虚拟化&Linux内核实习岗位](https://jobs.opennash.com/companies/kuaishou-technology/jobs/2a036b5c0a6b3e7f8cdb/)

Beijing, Shenzhen, 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/)