AI Research Engineer – Human Data

About the role

Flexion Robotics is looking for an AI Research Engineer specialized in human data to push the boundaries of generalizable manipulation for humanoid robots. You will bridge human embodiment and robotic execution using video demos, wearable capture systems, and other multimodal data sources.

Key responsibilities

• Develop scalable pipelines that integrate human video demonstrations, wearable systems (e.g., UMI, sensorized gloves) and unconstrained manipulation data into foundation model and reinforcement‑learning workflows.
• Build automated 3D reconstruction pipelines to create digital twins of manipulated objects and environments for simulation‑to‑real transfer.
• Design simulation environments with reconstructed assets and use reinforcement learning, tactile and force feedback to generate dexterous manipulation policies.
• Create and evaluate multimodal robot foundation models that translate multi‑sensor streams into robust control.
• Design algorithms that transfer human embodiment knowledge to high‑DOF dexterous hands and humanoid platforms.

Required profile

• PhD in Computer Science or a related field, or equivalent practical experience.
• Experience with vision, vision‑language, video and other multimodal models trained on human data.
• Hands‑on experience with reinforcement learning and imitation learning.

Required skills

• Vision and vision‑language modeling
• Multimodal video and sensor data processing
• Reinforcement learning and imitation learning
• Simulation environment creation and digital twin reconstruction
• Tactile and force‑feedback sensing

What we offer

• Competitive compensation and enhanced pension plan
• Generous holiday and paid‑leave perks
• Relocation assistance and permit sponsorship
• State‑of‑the‑art Zürich office with top‑tier robotics testing facilities
• Opportunity to join Europe’s leading robotics team and work on never‑done‑before research