[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

# 【基座大模型北斗实习】多模态后训练及 Agent 能力拓展

北京市 

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=4346347366)

[OpenNash Jobs](https://jobs.opennash.com/) / [Meituan ](https://jobs.opennash.com/companies/meituan/) / 【基座大模型北斗实习】多模态后训练及 Agent 能力拓展

## Job description

### 简介

跟踪多模态后训练前沿方法（SFT / DPO / GRPO 等），快速完成技术预研与可行性验证，形成可落地的训练方案并推动模型迭代。
- 面向复杂业务场景（如多轮交互、长序列推理、跨模态 Agent 决策等），进行针对性的垂域数据建设与指令微调，持续提升模型在垂直场景下的表现上限。
- 建设后训练评估体系与数据飞轮，设计面向垂域场景的自动化评测基准，驱动"评测→数据→训练→评测"的闭环迭代。
- 探索多模态大模型与新一代Agent框架（Claude Code、OpenClaw 等）的深度结合，研究模型在工具调用、环境感知、多步规划等场景下的能力边界，推动多模态模型从"被调用"向"自主交互"演进，拓展智能体在真实复杂环境中的落地路径。
- 对前沿技术有强烈的探索欲，有出色的团队协作精神；
- 有OpenClaw、Claude code深度使用经验与产出优先；
- 发表过领域顶级会议文章(NeurIPS、ICML、ICLR、ACL、Interspeech、ICASSP等)、ACM竞赛获奖者优先。

## 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[Apply on Meituan ’s careers site →](https://zhaopin.meituan.com/web/position/detail?highlightType=campus&jobUnionId=4346347366)

## More jobs at Meituan 

### [2027秋招-客服产品运营](https://jobs.opennash.com/companies/meituan/jobs/f978e7cc03c79468cf40/)

北京市

### [2027秋招-客服工具运营](https://jobs.opennash.com/companies/meituan/jobs/6aadb21477d2532eed03/)

北京市

### [3PL加工主管](https://jobs.opennash.com/companies/meituan/jobs/e9a43ac9d86f9eeb5ebd/)

北京市

### [AI Agent 产品经理](https://jobs.opennash.com/companies/meituan/jobs/9bcdd148de90945f1a23/)

北京市

### [AI Agent 产品经理（微信生态方向）](https://jobs.opennash.com/companies/meituan/jobs/0ee416ec313968c517be/)

北京市

## Similar jobs at other companies

### [Agent Polyvalent](https://jobs.opennash.com/companies/totalenergies/jobs/26f4ab20523024a02303/)

TotalEnergies 

### [Agent Méthodes](https://jobs.opennash.com/companies/totalenergies/jobs/1555594fdaccbae2a870/)

TotalEnergies 

### [Clearance Agent](https://jobs.opennash.com/companies/fedex/jobs/a3f51c1e7e4f2fb58ab1/)

FedEx 

### [Ramp Agent](https://jobs.opennash.com/companies/fedex/jobs/c40cbecd496eb57be950/)

FedEx 

### [AI Agent Engineer](https://jobs.opennash.com/companies/sk-square/jobs/d61bb3980a55979413ce/)

SK Square · Seoul

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/)