[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

# Agentic RL 算法实习生

北京 

Listed on Xiaomi ’s official careers site. Posted December 16, 2025. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/internship/position/7584418368922503467/detail)

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

## Job description

### RL训练环境搭建
- 负责构建易用、稳定且支持高并发的工具调用环境，搭建和优化 Agent 框架。

### 推理能力提升
- 针对 DeepResearch、CodeAgent 等复杂推理场景，设计并实现高效的能力增强方案。

### 数据合成与优化
- 围绕业务需求构建、筛选和优化 Agent 行为数据与知识增强语料，为对齐训练、RL 训练和持续预训练提供高质量数据支撑。

## Qualifications

### 任职要求
- 计算机相关专业；在CCF-A类会议发表过相关论文者优先考虑；
- 熟悉主流 Agent 框架（如 Claude Code、LangGraph、AgentScope、Qwen-Agent 等），具备实际开发或使用经验。
- 熟练掌握主流 Agentic RL 训练框架（如 VeRL、OpenRLHF），具备后训练（post-training）和数据处理相关项目经验者优先。
- 理解并掌握并行训练框架，有多机多卡训练经验者优先。

## At a glance
- Posted by the employer: Dec 16, 2025
- First seen by OpenNash: Aug 1, 2026
- Last checked: Oct 19, 2026
- Listed for: 307 days
- Location: 北京[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/internship/position/7584418368922503467/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

### [研究院-算法实习生-上海](https://jobs.opennash.com/companies/hikvision/jobs/0cab3c7c560c3b8ec63e/)

Hikvision · 上海市

### [萤石-算法实习生-杭州](https://jobs.opennash.com/companies/hikvision/jobs/736508baa3320a0e0952/)

Hikvision · 浙江省杭州市

### [算法实习生](https://jobs.opennash.com/companies/sany-heavy-industry/jobs/44d314c30bddc9d6c2da/)

Sany Heavy Industry · 北京市

### [算法实习生 -【综效线-企业应用部】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/2ec4fbe2a76a843dc516/)

Kuaishou Technology · Beijing

### [算法实习生 - 【综效线-效率工程部】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/c50348cd33c9af12272a/)

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/)