[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

# 多模态算法实习生

北京 

Listed on Xiaomi ’s official careers site. Posted October 15, 2026. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/internship/position/7696781346635237673/detail)

[OpenNash Jobs](https://jobs.opennash.com/) / [Xiaomi ](https://jobs.opennash.com/companies/xiaomi/) / 多模态算法实习生

## Job description
- 参与端侧全模态大模型研发，包括 Audio Encoder、Speech Tokenizer、LLM、Speech Decoder 等核心模块的技术调研、模型训练与优化。​
- 研究语音、文本、视觉等多模态信息的对齐与融合技术，开展语音理解、语音生成及跨模态联合训练。​
- 参与实时语音交互技术研发，包括流式语音生成、低延迟响应、语音打断及全双工交互等关键能力。​
- 参与多模态数据构建、数据清洗、模型训练及效果评测，持续优化模型性能。​
- 探索模型压缩、量化及推理加速技术，参与端侧模型部署与真机效果验证。

## Qualifications
- 计算机、人工智能、电子信息等相关专业在读硕士或博士研究生，具备扎实的机器学习、深度学习基础。
- 熟练掌握 Python、PyTorch 等开发工具，具备模型训练、调试及实验分析能力。
- 熟悉大语言模型或多模态大模型基本原理，在 Audio、TTS、VLM、Omni 等至少一个方向具有相关研究或项目经验。
- 具备良好的论文阅读、技术调研及算法复现能力，能够独立开展实验并分析问题。
- 具备良好的沟通协作能力，实习时间不少于3个月，每周到岗不少于4天，能够长期实习者优先。

## At a glance
- Posted by the employer: Oct 15, 2026
- First seen by OpenNash: Oct 19, 2026
- Last checked: Oct 19, 2026
- Listed for: 4 days
- Location: 北京[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/internship/position/7696781346635237673/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

### [多模态算法实习生](https://jobs.opennash.com/companies/kuaishou-technology/jobs/da319ddfbb3155ad9de8/)

Kuaishou Technology · Beijing

### [多模态算法实习生-【商业化】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/e38a90019bd78ca60d93/)

Kuaishou Technology · Beijing

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/)