多模态理解算法研究员/专家
上海、深圳
全职
职位描述
1、研发多模态理解模型：视觉-语言对齐、视频理解、场景语义/事件理解、指代消解； 2、攻关应用场景难点：开放世界泛化、长尾物体、复杂指代（那个/旁边/刚才）； 3、输出结构化语义表示：对象/属性/关系/事件/可操作性（affordance）等，便于规划调用； 4、建立评测与数据策略：线上失败归因、难例回流、版本对比与回归测试； 5、与Agent/规划/VLN协同，围绕任务成功率与稳定性闭环优化；
职位要求
1、熟悉 Transformer 基础与多模态基本范式（对齐、融合、token/embedding、评测）； 2、图文检索、grounding、VQA、视频理解、指代表达理解等任一方向科研背景； 3、能使用 PyTorch 复现 VLM/Video Understanding 相关工作，具备数据处理与训练经验； 加分项 - 具身语义/导航语义理解经验； - 数据合成、自动标注、弱监督经验； - 顶会论文/专利/高质量开源复现或贡献。
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.
