Shanghai
Full time
At Mentee Robotics, we are redefining humanoid automation with an AI-first approach - combining perception, reasoning, and dexterous manipulation into fully autonomous systems that continuously learn and adapt. 在 Mentee Robotics，我们以 AI 优先的理念重新定义人形机器人自动化——将感知、推理与灵巧操作融合为能够持续学习与自适应的全自主系统。 We are now expanding with a new robotics Engineering Center in China, working hand-in-hand with our engineering teams in headquarters. Its mission: to rapidly develop our next-generation full-size humanoid and bring it to life - a walking, working platform that becomes the foundation of our next generation of products. This is a small, senior, hands-on team where speed of iteration is the core value. 我们正在中国设立全新的机器人工程中心，与总部的工程团队紧密协作。其使命是：快速研发我们下一代全尺寸人形机器人并使其落地——一个能行走、能工作的平台，成为我们下一代产品的基础。这是一支精干、资深、亲力亲为的团队，迭代速度是其核心价值。 We are looking for a Motion Control Engineer to own the control algorithms of every joint in our humanoid - jointly with the embedded team, who implement your designs on the Motor Controller PCB. This is pure actuator control: FOC, loop design, estimation, and compensation. Whole-body behavior lives in learned policies; your job is to make every joint execute its commands perfectly. 我们正在寻找一位运动控制工程师，负责我们人形机器人每个关节的控制算法——与嵌入式团队共同协作，由其在电机控制器 PCBA 上实现你的设计。这是纯粹的执行器控制：FOC、环路设计、估计与补偿。全身行为由学习得到的策略承载；你的职责是让每个关节完美执行其指令。
Who you are期待中的你
- A motor control specialist who can take a noisy, nonlinear physical joint and make it track like a servo catalog page
- 一位电机控制专家，能够将一个充满噪声、非线性的物理关节调校得像伺服样本手册上的指标那样精准跟踪
- Equally fluent in control theory and in what the silicon can actually compute in a 60 kHz loop
- 既精通控制理论，又清楚芯片在60 kHz 控制环路中实际能完成的计算
- Data-driven: you tune with measurements, plots, and system identification - not by feel alone
- 数据驱动：你依靠测量、图表与系统辨识来调参——而非仅凭感觉
Responsibilities岗位职责
- Define and validate the motor control methodology across the robot: FOC and commutation strategies for BLDC motors in quasi-direct-drive configurations with planetary reduction
- 在整机范围内定义并验证电机控制方法论：针对采用行星减速的准直驱构型无刷直流电机的 FOC 与换相策略
- Design current, velocity, and position/torque control loops; define bandwidths, filtering, anti-windup, and saturation handling
- 设计电流、速度与位置/扭矩控制环；定义带宽、滤波、抗积分饱和与饱和处理
- Develop torque estimation, friction and cogging compensation, and observers for joint state
- 开发扭矩估计、摩擦与齿槽补偿，以及关节状态观测器
- Define joint-level safety limits and fault-handling behavior together with embedded
- 与嵌入式团队一起定义关节级安全限值与故障处理行为
- Guide and verify the embedded implementation of your algorithms on the Motor Controller PCB; co-own everything running on that board
- 指导并验证你的算法在电机控制器 PCBA 上的嵌入式实现；与团队共同负责该设计板子上运行的一切
- Design and execute structured characterization tests on the joint dyno: torque, speed, resolution, responsiveness, thermal behavior
- 在关节测功机上设计并执行结构化的特性测试：扭矩、转速、分辨率、响应性、热行为
- Deliver validated actuator models and control limitations to the Sim2Real and RL teams - your measured envelopes become their training constraints
- 向 Sim2Real 与强化学习团队交付经过验证的执行器模型与控制限制——你测得的工作包络将成为他们的训练约束
- Drive improvements in actuation repeatability and responsiveness through precise measurement and feedback
- 通过精确测量与反馈，推动执行重复性与响应性的提升
Requirements任职要求
- B.Sc. or M.Sc. in Electrical, Mechanical, or Control Engineering (or equivalent experience)
- 电气、机械或控制工程专业学士或硕士学位（或同等经验）
- 8+ years in motor control systems or motion system integration
- 8年以上电机控制系统或运动系统集成经验
- Deep hands-on experience with FOC and current/velocity/position loop design for BLDC motors
- 在无刷直流电机的 FOC 以及电流/速度/位置环设计方面具备深厚的动手经验
- Familiarity with planetary gear systems and QDD architectures, and their impact on control and sensing
- 熟悉行星齿轮系统与准直驱（QDD）架构，及其对控制与传感的影响
- Proven ability to define and lead performance test plans from lab setup to interpretation
- 具备从实验室搭建到结果解读全程定义并主导性能测试方案的成熟能力
- Comfortable using lab tools (oscilloscopes, encoders, current sensors) to evaluate dynamic behavior under load and in closed loop
- 能够熟练使用实验室工具（示波器、编码器、电流传感器）评估负载下及闭环中的动态行为
- Impedance control and proprioceptive actuation experience
- 具备阻抗控制与本体感知执行的经验
Advantages加分项
- Experience in robotic or humanoid actuation or servo drive companies
- 具备机器人或人形机器人执行（如宇树、无穹的执行器团队）或伺服驱动公司（如步科、汇川）的经验
- Familiarity with harmonic gear systems and their control implications
- 熟悉谐波齿轮系统及其对控制的影响
- Python for scripting, system identification, and data analysis
- 使用 Python 进行脚本编写、系统辨识与数据分析
- Understanding of how sensor noise, latency, and actuation limits affect learned whole-body policies
- 理解传感器噪声、延迟与执行限制如何影响学习得到的全身控制策略
- Comfortable communicating technical topics in English with international teams
- 能够用英语与国际团队就技术话题进行交流
