AGIBOT

语义动作生成算法工程师

AGIBOT  •  Shanghai, CN (Onsite)  •  3 hours ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

语义动作生成算法工程师

上海

全职

互联网 / 电子 / 网游

职位描述

结合TTS(文本转语音)的韵律特征(音素时长、基频、能量),生成与语音同步的口型、头部姿态、手势等副语言动作 设计多模态对齐机制,确保动作生成与语音合成的节奏、停顿、情感表达精准同步 构建语音合成与动作生成的流式协同框架,支持实时对话场景下的低延迟、高同步度输出 将算法能力封装为可复用的动作生成SDK/服务,支撑多元业务场景 与机器人控制、交互系统团队紧密协作,推动技术方案的产品化落地

职位要求

  • 计算机、机器人学、图形学、人工智能等相关专业硕士及以上学历,博士优先,3年以上相关领域研究或开发经验 •扎实的深度学习基础,精通PyTorch,有生成模型(Diffusion、VAE、GAN、Flow-based)的实际项目经验 •深入了解动作生成领域,熟悉MotionGPT、HumanML3D、MotionDiffusion、PhysDiff、ASE等代表性工作 •熟悉机器人运动学、计算机图形学中的角色动画基础,了解正向/逆向运动学、骨骼动画原理 •具备语音合成(TTS)相关基础知识,了解声学模型、声码器、韵律建模 熟悉动作表示与处理:SMPL/SMPL-X、BVH、AMC、运动学图(Kinematic Trees)、四元数/旋转矩阵表示 加分项 •顶级会议期刊论文发表 •有真实机器人平台或虚拟人引擎的实际落地经验 •熟悉实时动作生成管线,或有游戏/影视动画行业经验 •有语音合成(TTS)或语音识别(ASR)的深入研发经验,具备多模态联合训练经验 •熟悉物理驱动的动作生成、强化学习(RL)在动作控制中的应用 •有开源项目贡献或相关专利

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