AGIBOT

具身数据算法工程师

AGIBOT  •  Onsite  •  2 hours ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

具身数据算法工程师

上海

全职

职位描述

负责机器人数据闭环中的智能处理、自动标注与样本挖掘,构建高质量训练数据集,提升数据对模型训练的价值密度,实现“数据→模型”的高效转化。 【岗位职责】 · 基于多模态大模型(VLM/VLA)构建自动标注管线,对视频、动作轨迹、触觉信号等进行结构化标注(动作阶段、接触事件、成功/失败标签),降低人工标注成本; · 设计样本挖掘与筛选策略,运用主动学习与场景挖掘技术,从海量数据中识别高价值样本(失败轨迹、长尾场景、异常操作),提升训练集的多样性与任务覆盖度; · 开发数据增强方法(轨迹扰动、视角变换、动力学仿真合成),利用MimicGen/DexMimicGen等技术实现“单条演示→100-1000倍合成数据”,扩充高质量训练样本; · 建立数据质量评估模型,自动化过滤低质量样本,持续迭代标注与清洗策略,沉淀数据清洗标准作业流程(SOP); · 与生产、评测团队协同,快速响应模型训练中的数据痛点,推动数据-模型闭环优化。

职位要求

有自动驾驶、具身智能或大规模自动标注项目经验; - 熟悉VLA、Diffusion Policy、ACT等机器人学习算法,有相关算法开发经验; - 有模型微调或训练经验,了解LoRA、RLHF等高效微调技术; - 有仿真合成数据生成经验(MimicGen、Isaac Sim等); - 在机器人/计算机视觉顶会(CoRL、ICRA、IROS、CVPR等)发表过相关论文

投递

AGIBOT

About AGIBOT

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.

Industry
Manufacturing & Production
Company Size
201-500 employees
Headquarters
Shanghai, CN
Year Founded
Unknown
Social Media