[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

# Aios研发工程师-端云协同推理

北京 

Listed on Xiaomi ’s official careers site. Posted October 12, 2026. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/internship/position/7695730669293226267/detail)

[OpenNash Jobs](https://jobs.opennash.com/) / [Xiaomi ](https://jobs.opennash.com/companies/xiaomi/) / Aios研发工程师-端云协同推理

## Job description
- 跟进大模型端云协同推理前沿论文和成功实践，参与AI系统/端云推理框架核心技术的调研、开发与验证，输出行业领先的技术方案、论文或专利。

### 共同开展 AI Agent框架端云模型调度与协同推理方案的开发
- 根据任务特征、运行环境与资源约束，决策"在哪算、用哪个模型、怎么协同推理"，并持续迭代策略效果。
- 参与AI系统/ AI Agent 端云模型管理与运行时相关能力建设，保障多模型、多场景下的推理效率与稳定性。
- 跟进大模型推理优化、模型压缩/加速、系统工程等方向的前沿进展，围绕时延、吞吐、成本、效果等核心指标做性能分析与优化，参与技术研讨和技术分享。

## Qualifications
- 计算机、人工智能、软件工程、电子信息等相关专业在读硕士/博士，每周可到岗 4 天及以上。
- 了解深度学习与大模型基本原理，对大模型的推理优化技术有基本认知。
- 扎实的编程基础,熟悉 Python / C++ / Java / Kotlin 中至少一种；学习能力强，能快速上手新技术栈。
- 有 AI Agent、推理编排或工具调用链路相关的研究或开发经验者优先。

## At a glance
- Posted by the employer: Oct 12, 2026
- First seen by OpenNash: Oct 19, 2026
- Last checked: Oct 19, 2026
- Listed for: 7 days
- Location: 北京[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/internship/position/7695730669293226267/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/)