[Skip to main content](#main-content)

[OpenNash Jobs](https://jobs.opennash.com/)
[Hiring report](/reports/hiring/) · [All Meituan jobs](https://jobs.opennash.com/companies/meituan/) · [Search jobs](/search/)

Meituan · 北京市 +1 more

# 【大模型北斗实习】大规模 Post-training 算法架构前沿研究

北京市 +1 more Education & Training 

Listed on Meituan ’s official careers site. Listed as of October 19, 2026. Check that it is still open and apply there.
[Apply on Meituan ’s careers site →](https://zhaopin.meituan.com/web/position/detail?highlightType=campus&jobUnionId=3153937173)

[OpenNash Jobs](https://jobs.opennash.com/) / [Meituan ](https://jobs.opennash.com/companies/meituan/) / 【大模型北斗实习】大规模 Post-training 算法架构前沿研究

## Job description

Post-training 是提升大模型专项能力的核心技术方向之一，包括不限于复杂推理（Reasoning）、价值观对齐（Alignment）、业务Agent应用等研究方向。

### 本课题研究方向包括但不限于

1）实现高效灵活的多模型强化学习训练架构。 2）通过合理灵活动态配置资源，提升PPO及各变种算法运行效率。 3）研究低精度在 Post-training 中的应用方式。 4）研究不同的算法+数据对效果的影响。 5）在复杂框架下，研究如何高效的追踪记录训练过程，提升算法探索效率。 1）熟悉大规模分布式训练、推理、量化等技术之一。 2）熟悉常用的训练推理框架，vLLM、SGLang、Megatron、Deepspeed等。 3）熟悉强化学习算法。

### 加分项

相关领域开源项目或发表高水平论文。

## At a glance
- Posted by the employer: Not stated
- First seen by OpenNash: Oct 19, 2026
- Last checked: Oct 19, 2026
- Listed for: Under a day
- Location: 北京市 +1 more[Apply on Meituan ’s careers site →](https://zhaopin.meituan.com/web/position/detail?highlightType=campus&jobUnionId=3153937173)

## More jobs at Meituan 

### [【LongCat大模型人才校招】基础大模型 Post-training 算法研究员](https://jobs.opennash.com/companies/meituan/jobs/a6bf93eec59f0a90e72b/)

北京市 +1 more

### [【LongCat实习】LongCat 大模型研究员-Post-training](https://jobs.opennash.com/companies/meituan/jobs/38f5e57d0ee1b6d36295/)

北京市 +1 more

### [【大模型北斗实习】Post-training 前沿算法研究](https://jobs.opennash.com/companies/meituan/jobs/234119d217723c851edb/)

北京市 +1 more

### [基座大模型算法研究员 (Mid-training)](https://jobs.opennash.com/companies/meituan/jobs/34d587da142af5ad45a1/)

北京市 +1 more

### [AI Agent 产品经理](https://jobs.opennash.com/companies/meituan/jobs/2b6311eacacf7247913a/)

北京市 +1 more

## Similar jobs at other companies

### [Senior Applied Scientist(Agentic RL & LLM Post-Training)](https://jobs.opennash.com/companies/microsoft/jobs/f6fc9eb08b2e90052149/)

Microsoft · China, Jiangsu, Suzhou, Beijing

### [Solutions Architect, Pre-training and Post-training](https://jobs.opennash.com/companies/nvidia/jobs/2d283936adc915b8ca63/)

NVIDIA · Korea, Seoul

### [Senior Manager, Software Engineering - RL Post-Training Frameworks](https://jobs.opennash.com/companies/nvidia/jobs/30ae8846ec825cb49c2f/)

NVIDIA 

### [SLM & VLM Engineer — Post-Training, Tool Calling & Agents](https://jobs.opennash.com/companies/jabil-circuit/jobs/0242da7262e088f4d604/)

Jabil Circuit · Singapore

### [AIML - Foundation Model Post-Training Research Scientist](https://jobs.opennash.com/companies/apple/jobs/3fd3341996a6651a5cc9/)

Apple · Zurich, Switzerland

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/)