Reinforcement Learning Engineer - Whole-Body Control

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 an RL Engineer to train the whole-body behaviors of our humanoid in simulation, on Isaac Sim with the Newton physics engine. In our architecture there is no classical motion controller above the joint level - the learned policy is the robot's entire behavior layer, coordinating all degrees of freedom and commanding joints directly through the actuator controllers. You are on the critical path to the robot's first steps.

我们正在寻找一位强化学习工程师，在使用 Newton 物理引擎的 Isaac Sim 仿真中训练我们人形机器人的全身行为。在我们的架构中，关节层之上并没有经典的运动控制器——学习得到的策略就是机器人的整个行为层，协调所有自由度并通过执行器控制器直接指挥关节。你处于机器人迈出第一步的关键路径上。

Who you are 期待中的你

A deep RL practitioner who has actually transferred policies to physical legged robots - not only benchmarks
一位真正将策略迁移到实体足式机器人的深度强化学习实践者——而不仅停留在基准测试
Strong engineer first: your training code is infrastructure, not a notebook
首先是一名出色的工程师：你的训练代码是基础设施，而非一个 notebook
Comfortable being the owner of the robot's most visible capability
乐于成为机器人最显眼能力的负责人

Responsibilities 岗位职责

Design, train, and iterate whole-body RL policies in Isaac Sim/Newton: walking, balance recovery, manipulation, and coordinated loco-manipulation behaviors
在 Isaac Sim/Newton 中设计、训练并迭代全身强化学习策略：行走、平衡恢复、操作以及协调的移动-操作行为
Own reward design, curriculum learning, and training methodology; incorporate motion priors (mocap/imitation, AMP-style) for natural movement
负责奖励设计、课程学习与训练方法论；引入运动先验（动作捕捉/模仿、AMP 式）以实现自然的动作
Build and maintain the training infrastructure: massively parallel simulation, experiment tracking, evaluation suites
构建并维护训练基础设施：大规模并行仿真、实验跟踪、评估套件
Work with the Sim2Real engineer to bake measured actuator constraints and domain randomization into training
与 Sim2Real 工程师协作，将实测的执行器约束与域随机化融入训练
Work with the compute platform engineer to deploy policies on the robot and run on-hardware evaluation
与计算平台工程师协作，在机器人上部署策略并进行在机评估
Progressively expand the policy's capability envelope - from first steps to dynamic, contact-rich whole-body tasks
逐步扩展策略的能力边界——从迈出第一步到动态、富接触的全身任务
Define what the policy observes and commands together with motion control and platform teams - you co-own the robot's core software contract
与运动控制及平台团队一起定义策略所观测与指挥的内容——你将共同负责机器人核心的软件契约

Requirements任职要求

M.Sc. or Ph.D. (or equivalent industry experience) in Computer Science, Robotics, or a related field
计算机科学、机器人或相关专业硕士或博士学位（或同等行业经验）
5+ years of hands-on deep RL for robotics with strong PyTorch engineering skills
5年以上面向机器人的深度强化学习实战经验，并具备扎实的 PyTorch 工程能力
Direct experience with Isaac Sim/Newton (or equivalent GPU-parallel simulators) for whole-body RL on legged robots
具备直接使用 Isaac Sim/Newton（或同类 GPU 并行仿真器）在足式机器人上进行全身强化学习的经验
Proven sim-to-real transfer of at least one policy to a physical legged robot
有将至少一项策略成功从仿真迁移到实体足式机器人的过往业绩
Deep understanding of PPO-family training at scale, reward shaping, and curriculum design
深入理解大规模 PPO 系列训练、奖励塑形与课程设计

Advantages加分项

Familiarity with IsaacLab
熟悉 IsaacLab
Humanoid (vs. quadruped) whole-body RL experience
具备人形（相对于四足）全身强化学习经验
Experience with motion-imitation methods (AMP, DeepMimic-style) and mocap data pipelines
具备运动模仿方法（AMP、DeepMimic 式）与动作捕捉数据流水线的经验
Publications in top robotics/ML venues (RSS, CoRL, ICRA, NeurIPS) or experience at leading humanoid teams
在顶级机器人/机器学习会议（RSS、CoRL、ICRA、NeurIPS）发表论文，或曾在领先的人形机器人团队任职的经历
Experience with teleoperation or demonstration data pipelines for whole-body skills
具备面向全身技能的遥操作或示教数据流水线的经验
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