[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 · 深圳

# 顶尖应届-端侧大模型算法工程师-软件

深圳 

Listed on Xiaomi ’s official careers site. Posted June 4, 2026. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/toptalent/position/7647448387089320238/detail)

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

## Job description
- 负责大模型在内的各类算法的移动端部署与优化；
- 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
- 信号处理/模式识别/人工智能等相关专业毕业，熟练使用C/C++；
- 对深度学习有深刻认识，熟悉各种神经网络及背后数学原理，熟悉各类神经网络模型的量化/压缩/性能优化方案；
- 对大模型加速优化方案有深入了解，对投机采样，GQA，MOE，Lora量化等技术有开发与优化经验者优先；
- 有TFlite (Micro)，NCNN，SNPE/QNN，EAI，NeuroPilot等移动端深度学习框架开发经验者优先；
- 熟悉神经网络模型的定点优化，熟悉各类嵌入式平台芯片架构及底层指令，有ARM Neon、Hexagon DSP、Cadence Hifi3/5、RISC-V等平台的算子开发及算法调优经验者优先；
- 有相关领域高质量会议/期刊论文，或深度参与过开源深度学习框架的开发并有相应贡献者优先。

## At a glance
- Posted by the employer: Jun 4, 2026
- First seen by OpenNash: Aug 1, 2026
- Last checked: Oct 19, 2026
- Listed for: 137 days
- Location: 深圳[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/toptalent/position/7647448387089320238/detail)

## More jobs at Xiaomi 

### [AI Agent开发工程师](https://jobs.opennash.com/companies/xiaomi/jobs/b6d78153a2ad67ccdb4f/)

深圳

### [BSP底层专家](https://jobs.opennash.com/companies/xiaomi/jobs/d5d898b5e9a64be314bb/)

深圳

### [GTM专员](https://jobs.opennash.com/companies/xiaomi/jobs/e202fdb1f52d0445d09a/)

深圳

### [Sram版图设计工程师](https://jobs.opennash.com/companies/xiaomi/jobs/25cc7ad2bad44f09c0c0/)

深圳

### [SoC芯片验证实习生-2027届](https://jobs.opennash.com/companies/xiaomi/jobs/d506fd60a52b9a6ffd60/)

深圳

## Similar jobs at other companies

### [端侧大模型算法工程师](https://jobs.opennash.com/companies/geely-automobile-holdings/jobs/b3e336c2f90b79f22a17/)

Geely Automobile Holdings · 上海市, 中国

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/)