[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-多模态推理加速研究员-AI基建

北京 

Listed on Xiaomi ’s official careers site. Posted October 9, 2026. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/topintern/position/7694626442655058186/detail)

[OpenNash Jobs](https://jobs.opennash.com/) / [Xiaomi ](https://jobs.opennash.com/companies/xiaomi/) / 顶尖实习-多模态推理加速研究员-AI基建

## Job description

- 负责多模态模型(图像、视频、音频等) 模型适配，性能分析和推理优化，支持实时语音和视频输入和输出 - 负责基于SGLang 等技术的多模态推理框架的开发和优化，包括分布式推理架构，推理引擎， 多模态cache管理，算子优化等 - 负责扩散模型推理优化包括并行优化，稀疏化，cache管理等，以及与语言模型推理架构统一

## Qualifications

- 硕士及以上学历，计算机、软件工程、数学等相关专业，具备扎实计算机理论基础和丰富编程经验
- 精通 Python，熟练掌握至少一种深度学习框架（如 PyTorch），理解深度学习基础算法原理，熟悉基础Transformer，ViT， DiT等模型结构优先
- 熟悉大模型推理框架的基本原理和流程，了解 vLLM、SGLang, diffusers等推理框架的核心技术和实现优先
- 有良好团队协作与沟通能力，强烈的上进心和自我驱动，挑战自我不断追求卓越；

## At a glance
- Posted by the employer: Oct 9, 2026
- First seen by OpenNash: Oct 19, 2026
- Last checked: Oct 19, 2026
- Listed for: 10 days
- Location: 北京[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/topintern/position/7694626442655058186/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

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/)