Sim2Real Engineer虚实迁移仿真工程师

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。

Who you are 期待中的你

A physics-minded engineer who treats simulation fidelity as an engineering discipline, not an afterthought
一位具备物理思维的工程师，将仿真保真度视为一门工程学科，而非事后补救
Rigorous about system identification - you fit models to measured data
对系统辨识严谨认真——你用实测数据拟合模型
A natural bridge between the hardware lab and the training cluster
在硬件实验室与训练集群之间天然的桥梁

Responsibilities岗位职责

Build and maintain the robot's digital twin (URDF/MJCF/USD) directly from the team's CAD, tracking every hardware revision
直接基于团队的 CAD 构建并维护机器人的数字孪生（URDF/MJCF/USD），跟踪每一次硬件改版
Model actuators from real dyno data: torque-speed envelopes, friction, backlash, latency, and thermal limits - so trained policies never demand what hardware cannot deliver
依据真实测功机数据为执行器建模：扭矩-转速包络、摩擦、回差、延迟与热极限——使训练得到的策略绝不会要求硬件无法提供的能力
Run system identification campaigns against the physical robot together with motion control and V&V
与运动控制及验证团队（V&V）一起，针对实体机器人开展系统辨识工作
Design domain randomization strategies and simulation environments in Isaac Sim with the Newton physics engine, together with the RL engineer
与强化学习工程师一起，在使用 Newton 物理引擎的 Isaac Sim 中设计域随机化策略与仿真环境
Own the sim-to-hardware deployment pipeline together with the compute platform engineer: export, validation, and on-robot evaluation protocols
与计算平台工程师一起负责从仿真到硬件的部署流水线：导出、验证以及在机评估流程
Quantify and continuously reduce the sim-to-real gap with defined metrics
用明确的指标量化并持续缩小仿真与现实之间的差距
Generate synthetic data and scenario suites for training and regression testing
生成用于训练与回归测试的合成数据与场景集

Requirements任职要求

M.Sc. (or equivalent experience) in Robotics, Mechanical/Electrical Engineering, or Computer Science
机器人、机械/电气工程或计算机科学专业硕士学位（或同等经验）
4+ years with physics simulation for robotics: Isaac Sim/Newton, MuJoCo, or equivalent
4 年以上面向机器人的物理仿真经验：Isaac Sim/Newton、MuJoCo 或同类工具
Strong Python; solid grasp of rigid-body dynamics, contact modeling, and actuator dynamics
扎实的 Python 能力；牢固掌握刚体动力学、接触建模与执行器动力学
Hands-on system identification experience against physical hardware
具备针对实体硬件进行系统辨识的动手经验
Experience supporting RL policy transfer to real robots (domain randomization, dynamics randomization, actuator modeling)
具备支持强化学习策略迁移到真实机器人的经验（域随机化、动力学随机化、执行器建模）

Advantages加分项

Sim2Real work on legged or humanoid robots
在足式或人形机器人上从事 Sim2Real 工作的经验
Experience with USD pipelines and CAD-to-sim automation
具备 USD 流水线与 CAD 到仿真自动化的经验
Familiarity with Motor Operating Region style actuator-constraint modeling in training
熟悉训练中以电机工作区（Motor Operating Region）方式进行的执行器约束建模
C++ for high-performance simulation components
使用 C++ 编写高性能仿真组件
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