多模态生成动作大模型工程师/专家
深圳、上海
全职
职位描述
1、研发多条件动作生成:文本/语音韵律/视觉条件→全身动作与手势; 2、研究可控生成:风格、人设、情绪、节奏、强约束(空间/安全/可执行)下的生成; 3、解决可执行性:动力学约束、接触与平衡、IK约束、动作拼接与过渡自然性; 4、评测与数据:动作自然度、稳定性、可执行性、审美与一致性指标;线上A/B与回归; 5、与TTS/对话/控制/安全协作:打通“说什么→怎么说→怎么动”的闭环;
职位要求
1、熟悉动作生成/扩散模型/序列模型等,有研究与落地能力; 2、具备运动学基础:IK/约束、动作拼接过渡、抖动/不稳定识别与处理思路; 3、有项目/科研:Text2Motion、Speech2Motion、风格控制、韵律对齐等任一方向; 加分项: 熟悉动作生成/扩散模型/序列模型等,有研究与落地能力; 具备运动学基础:IK/约束、动作拼接过渡、抖动/不稳定识别与处理思路; 有项目/科研:Text2Motion、Speech2Motion、风格控制、韵律对齐等任一方向。
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.