大模型算法工程师-强化学习
上海
全职
职位描述
1、框架开发与优化:负责强化学习、模型精调、知识蒸馏等核心模块的设计与开发; 2、工具链构建:参与开发轻量化训练框架,支持LLM、VLM等模型的快速模型微调、部署; 3、前沿技术探索:跟踪学术动态,将最新研究成果转化为框架功能,提升产品竞争力; 4、协作与文档:与产品团队紧密配合,提供框架级解决方案;
职位要求
1、计算机科学、数学、电子工程等相关专业硕士及以上学历,精通Python; 2、有Megatron-LM、DeepSpeed等开源框架使用或二次开发经验,理解分布式训练、显存优化技术; 3、熟悉 GRPO/PPO 等 RL 算法、veRL/Slime/AReaL等强化学习框架者优先; 4、工程经验上具备大型项目架构设计能力,能独立解决性能调优、多节点调试等复杂问题; 5、综合素养;强烈的技术热情,良好的沟通能力与团队协作精神。 加分项 1、在顶级会议发表过框架优化或算法相关论文; 2、活跃于开源社区(如PyTorch、HuggingFace项目贡献者); 3、有LLM训练、RLHF全流程开发经验。
投递

AGIBOT is an Embodied AI foundation model company developing both the intelligence layer and the corresponding robotic embodiments needed to bring general intelligence into the physical world. Founded in 2023, AGIBOT is building a full-stack Embodied AI platform across foundation models, data infrastructure, simulation, robotic hardware, and deployment. AGIBOT’s “Three Intelligences in One” architecture integrates Locomotion Intelligence, Interaction Intelligence, and Manipulation Intelligence into a unified embodied system. AGIBOT’s portfolio spans humanoid robots, quadrupeds, dexterous systems, and commercial cleaning solutions. In March 2026, AGIBOT announced that its 10,000th robot had rolled off the production line.