About EASEEASE builds active, AI-powered exoskeletons for logistics and manufacturing. As a TUM spin-off, we have just started series production, and paid pilots with well-known logistics companies have led to first purchase orders. Our goal: move every parcel better, manually with an exoskeleton or autonomously with a robot.The roleOur exoskeletons are deployed in real warehouses and production plants and capture what video-only datasets miss: body pose, joint kinematics, interaction torques, vision, and hand forces from real human work. Your job is to turn that data into skills our humanoid can actually perform, so that human workers and robots can work side by side on the same tasks.What you'll doMap human motion onto humanoid kinematics and close the embodiment gapTrain manipulation and whole-body policies with imitation and reinforcement learningEvaluate in Isaac Lab or MuJoCo and on our in-house humanoid, and measure the value of our dataDefine what data training needs and help build our training setup, including GPU computeTurn new research on robot foundation models and VLAs into prototypesWhat you bringMaster's or PhD in robotics, CS, ML or similar, with hands-on experience from industry or researchImitation or reinforcement learning on real robots (e.g. Diffusion Policy, ACT, PPO)Strong Python and PyTorch; C++ is a plusPhysics simulation and sim-to-real transferSolid kinematics, dynamics and controlNice to haveLearning from human data (egocentric video, motion capture, retargeting)Humanoids, legged robots or exoskeletons; publications at CoRL, RSS, ICRA or NeurIPSDon't tick every box? Apply anyway. What you have built matters more than a perfect match.What we offerData almost nobody else has, from a product in series deploymentOur own humanoid and the chance to build Physical AI at the company from the ground upCompetitive salary plus virtual stock options (VSOP)Flexible hours, hybrid in Munich, mobility benefitBudget for conferences and further trainingMartin Fleischer, CEO & Co-Founderthe company is an equal opportunity employer. Applicants need a valid work permit for the EU.
Robot Learning Engineer, Human Motion Data (m/f/d) in Großmehring Arbeitgeber: EASE
EASE – Ergonomische Assistenzsysteme GmbH ist ein innovatives Start-up, das sich der Entwicklung von Exoskeletten widmet, um die Arbeitswelt gesünder und effizienter zu gestalten. Wir bieten dir die Möglichkeit, in einem dynamischen Umfeld mit kurzen Entscheidungswegen und offener Kommunikation zu arbeiten, während du direkt an der Schnittstelle von Technologie und Menschlichkeit mitwirkst. Bei uns hast du nicht nur die Chance auf persönliche Weiterentwicklung durch enge Zusammenarbeit mit dem Gründerteam, sondern auch die Möglichkeit, ein sinnstiftendes Produkt aktiv mitzugestalten.