AGIBOT

强化学习仿真工程师

AGIBOT  •  Onsite  •  18 hours ago
Apply
AI can make mistakes so check important info. Chat history is never stored.

Job Description

强化学习仿真工程师
上海
全职
互联网 / 电子 / 网游
职位描述
- 负责面向强化学习训练的大规模并行仿真能力研发与优化,为具身智能策略训练与评测提供高吞吐、高保真的仿真环境
- 负责仿真引擎与物理、渲染仿真能力的集成、扩展与优化,支撑机器人本体的运动学、动力学建模及操作交互仿真;
- 负责打通强化学习训练框架与仿真系统的对接,构建大规模并行采样与训练闭环,支持算法团队高效迭代;
- 负责面向强化学习训练的仿真任务库、场景库与评测体系(benchmark)的建立、维护与应用;
- 负责 sim-to-real / real-sim-real 相关能力研发,持续提升仿真真实性与策略的 sim-to-real 迁移率;
- 调研仿真与强化学习领域最新算法和技术并落地,突破现有仿真工具的能力瓶颈。
职位要求
-本硕及以上学历,优先计算机科学、数据科学、机器人、人工智能等相关专业;
- 精通 Linux 和 Docker 开发环境,熟悉 C++、Python 等编程语言,掌握规范 git 工作流,具备良好编程规范与系统级调试定位能力;
- 精通 Isaac Sim / MuJoCo / Genesis 等至少一种机器人仿真软件,能够搭建复杂的仿真场景,深入理解接触动力学、碰撞检测算法、数值求解器、刚体动力学和数值积分;
- 熟悉强化学习及其训练框架(如 RLinf、Stable-Baselines3、SERL 等),理解并行仿真环境、on/off-policy 训练与大规模采样机制;
- 熟悉 GPU 编程与加速(CUDA / NVIDIA Warp / PyTorch),对并行仿真、渲染管线、训练数据吞吐优化、分布式强化学习框架搭建有实践经验者优先;
- 熟悉 ROS / DDS / AimRT 等机器人系统通信中间件,对机器人传感器系统、机器人操作、运动控制有一定了解;
- 有通过系统辨识、域随机化等方式优化sim to real落地效果经验者优先。
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