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

[OpenNash Jobs](https://jobs.opennash.com/)
[Hiring report](/reports/hiring/) · [All Xiaomi jobs](https://jobs.opennash.com/companies/xiaomi/) · [Search jobs](/search/)

Xiaomi · 北京

# 顶尖实习-大模型推理加速研究员-AI平台

北京 

Listed on Xiaomi ’s official careers site. Posted October 14, 2026. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/topintern/position/7696343749215160602/detail)

[OpenNash Jobs](https://jobs.opennash.com/) / [Xiaomi ](https://jobs.opennash.com/companies/xiaomi/) / 顶尖实习-大模型推理加速研究员-AI平台

## Job description
- 参与和负责开源vllm/sglang推理引擎核心功能开发
- 负责大语言模型线上推理框架的性能优化，解决高并发、低延迟、高可靠性等核心问题，提升服务吞吐量与稳定性
- 调研并引入前沿技术，包括模型量化、蒸馏等轻量化开发

## Qualifications

### 学历背景
- 计算机/电子/数学等相关专业硕士及以上学历

### 编程能力
- 精通C/C++，熟悉Python，具备扎实的数据结构与算法基础，ACM/ICPC、NOI等竞赛获奖者优先

### GPU与CUDA
- 熟悉NVIDIA GPU架构及编程模型，掌握CUDA核函数优化、显存管理、多流并发等技术，有实际性能调优经验

### 框架与工具
- 熟悉PyTorch、Megatron、vLLM/SGLang等深度学习训练和推理框架优先

## At a glance
- Posted by the employer: Oct 14, 2026
- First seen by OpenNash: Oct 19, 2026
- Last checked: Oct 19, 2026
- Listed for: 5 days
- Location: 北京[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/topintern/position/7696343749215160602/detail)

## More jobs at Xiaomi 

### [27届招聘实习生-国际职能平台](https://jobs.opennash.com/companies/xiaomi/jobs/6d4d527313cd96474e53/)

北京

### [AI Agent 产品经理](https://jobs.opennash.com/companies/xiaomi/jobs/fc2f52865a7e2d84fbd7/)

北京

### [AI Agent 架构师 / Tech Lead](https://jobs.opennash.com/companies/xiaomi/jobs/35dcfe12c39db2a6a88a/)

北京

### [AI Agent产品经理](https://jobs.opennash.com/companies/xiaomi/jobs/1b2859d295836fa011a9/)

北京

### [AI Agent研究员实习生-小爱](https://jobs.opennash.com/companies/xiaomi/jobs/0c7ddc4025af5dc78885/)

北京

## Similar jobs at other companies

### [AI产品经理-AI平台（Agent）方向](https://jobs.opennash.com/companies/tencent-holdings/jobs/bbce89103daaee63d9cc/)

Tencent Holdings · Shenzhen

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/)