[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 · 南京

# 顶尖应届-端侧大模型工程师-软件

南京 

Listed on Xiaomi ’s official careers site. Posted June 5, 2026. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/toptalent/position/7646709706996795711/detail)

[OpenNash Jobs](https://jobs.opennash.com/) / [Xiaomi ](https://jobs.opennash.com/companies/xiaomi/) / 顶尖应届-端侧大模型工程师-软件

## Job description
- 负责大模型在内的各类算法的电视端部署与优化；
- 负责移动端深度学习框架开发及算子优化；
- 不断挖掘移动芯片算力潜能，改良模型结构，实现业界领先的算法执行效能；
- 撰写相关论文，专利。

## Qualifications
- 硕士及以上学历，计算机科学、电子通信信息等相关专业，博士优先；
- 在图像模式识别、机器学习、机器人学等领域有应用经验；
- C/C++及Python/Matlab 建模仿真编程方面有开发经验；

### 熟悉机器学习与深度学习相关理论
- BP, CNN, RNN, LSTM, SVM。有使用人工智能常用DL框架经验 （如TensorFlow, PyTorch, Caffe)；
- 熟悉基本的数字信号处理方法，如傅里叶变换、小波变换， 信号滤波、图像特征提取等算法实现；
- 有计步算法、地磁算法、场景感知算法、毫米波、vSLAM算法、人脸识别、手势识别的经验者优先。

## At a glance
- Posted by the employer: Jun 5, 2026
- First seen by OpenNash: Aug 1, 2026
- Last checked: Oct 19, 2026
- Listed for: 136 days
- Location: 南京[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/toptalent/position/7646709706996795711/detail)

## More jobs at Xiaomi 

### [AI Agent产品经理](https://jobs.opennash.com/companies/xiaomi/jobs/576879c80fdeb1ef535b/)

南京

### [AI Agent开发工程师-汽车](https://jobs.opennash.com/companies/xiaomi/jobs/d3e9df606c43c6c67e58/)

南京

### [Aios 开发工程师](https://jobs.opennash.com/companies/xiaomi/jobs/65202368107e11ee48b6/)

南京

### [AI属性工程师](https://jobs.opennash.com/companies/xiaomi/jobs/e945edb6ec7d10abfc53/)

南京

### [AI属性工程师-2027届](https://jobs.opennash.com/companies/xiaomi/jobs/afac799c7e81fa8a813e/)

南京

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/)