美团【基座大模型北斗实习】大模型后训练研究
实习兼职核心本地商业-基础研发平台地点:北京 | 上海状态:招聘
工作描述
任职要求 1、了解 PPO / GRPO / DPO 算法原理,最好动手实现过; 2、用过 veRL / OpenRLHF / TRL 等RL训练框架; 3、有 vLLM / SGLang / TensorRT-LLM 推理加速经验(rollout优化必备); 4、做过多机多卡训练,理解显存管理和通信开销; 5、RL系统相关顶会论文(NeurIPS/ICML/ICLR/MLSys)。 工作职责 简介:负责大规模强化学习系统设计、分布式调优、调度优化、算法 co-design等,包括不限于 …
登录查看完整工作描述
微信扫码,1秒登录
包括英文材料
算法+
https://roadmap.sh/datastructures-and-algorithms
Step by step guide to learn Data Structures and Algorithms in 2025
https://www.hellointerview.com/learn/code
A visual guide to the most important patterns and approaches for the coding interview.
https://www.w3schools.com/dsa/
大模型+
https://www.youtube.com/watch?v=xZDB1naRUlk
You will build projects with LLMs that will enable you to create dynamic interfaces, interact with vast amounts of text data, and even empower LLMs with the capability to browse the internet for research papers.
https://www.youtube.com/watch?v=zjkBMFhNj_g
vLLM+
https://www.newline.co/@zaoyang/ultimate-guide-to-vllm--aad8b65d
vLLM is a framework designed to make large language models faster, more efficient, and better suited for production environments.
https://www.youtube.com/watch?v=Ju2FrqIrdx0
vLLM is a cutting-edge serving engine designed for large language models (LLMs), offering unparalleled performance and efficiency for AI-driven applications.
SGLang+
[英文] Install SGLang
https://docs.sglang.ai/get_started/install.html
SGLang is a fast serving framework for large language models and vision language models.
https://github.com/sgl-project/sgl-learning-materials
还有更多 •••
相关职位
实习核心本地商业-基
1、硕士及以上学历,计算机、人工智能、数学等相关专业,博士优先; 2、熟悉NLP、LLM、RL等相关领域,对其中一个或多个方向有深入的研究经历,且有相关实践经验; 3、有较强的分析和解决问题能力,能够
更新于 2026-04-03北京|上海
实习核心本地商业-基
1、对前沿技术有强烈的探索欲,有出色的团队协作精神; 2、有OpenClaw、Claude code深度使用经验与产出优先; 3、发表过领域顶级会议文章(NeurIPS、ICML、ICLR、ACL、I
更新于 2026-04-03北京
实习核心本地商业-基
1、有好奇心,敢想敢做,学习能力强,能在复杂问题的深度思考与拆解能力; 2、在 Agentic RL、过程奖励(PRM)或复杂代码推理等方向有深入研究及顶会论文发表(ACL/EMNLP/NeurIPS
更新于 2026-04-03北京|上海