[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

# 大模型推理优化工程师

北京 

Listed on Xiaomi ’s official careers site. Posted August 24, 2026. Check that it is still open and apply there.
[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/campus/position/7677560508526725414/detail)

[OpenNash Jobs](https://jobs.opennash.com/) / [Xiaomi ](https://jobs.opennash.com/companies/xiaomi/) / 大模型推理优化工程师

## Job description
- 参与大模型推理优化和计算框架的设计与开发，探索提升推理效率的技术方案；
- 学习并应用量化、并行计算、访存优化等方法，协助优化模型推理时延和吞吐；
- 参与模型性能分析与调优实践，定位并解决性能瓶颈问题；
- 参与自动化工具和流程的开发，简化模型推理部署流程；
- 跟踪大模型推理领域最新研究进展，提出创新想法并推动落地。

## Qualifications
- 计算机、数学、人工智能等相关专业本科及以上学历，2027届毕业生；
- 扎实的编程基础，熟练掌握 C++/Python，有良好的代码风格和工程习惯；
- 了解机器学习/深度学习基础知识，熟悉 PyTorch 等主流框架；
- 对大模型推理优化方向有浓厚兴趣，了解 vLLM、SGLang 等推理框架者优先；

### 有以下任一经验者优先
- 参与过开源项目或推理框架社区贡献；
- 有 CUDA/GPU 编程、高性能计算相关实践经验（有github相关项目）；
- 有模型量化（GPTQ/AWQ/FP8等）、算子优化、内存优化等方向的实践或研究经历；
- 有投机采样（Speculative Decoding）、Medusa/EAGLE/MTP/DFlash 等加速解码相关经验；
- 有强化学习（RLHF/GRPO/DPO）训练或推理相关经验；
- 具备学术论文阅读与复现能力；
- 良好的学习能力、沟通能力和团队协作精神。

## At a glance
- Posted by the employer: Aug 24, 2026
- First seen by OpenNash: Oct 19, 2026
- Last checked: Oct 19, 2026
- Listed for: 56 days
- Location: 北京[Apply on Xiaomi ’s careers site →](https://xiaomi.jobs.f.mioffice.cn/campus/position/7677560508526725414/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

### [大模型推理优化工程师-【可灵AI专项】](https://jobs.opennash.com/companies/kuaishou-technology/jobs/a8a8a04034b41bfc4ad0/)

Kuaishou Technology · Beijing, Shanghai

### [微信 -WeLM 大模型推理优化工程师（深圳、上海）](https://jobs.opennash.com/companies/tencent-holdings/jobs/01564724afcaafc31778/)

Tencent Holdings · Beijing

### [腾讯专有云-大模型推理优化工程师-深圳/北京](https://jobs.opennash.com/companies/tencent-holdings/jobs/64849016b3890a28b30a/)

Tencent Holdings · Shenzhen

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/)