Research Fellow (Robot Learning & Manipulation)

About the role

SHARE@NTU Corporate Laboratory is seeking a Research Fellow to advance learning‑based visuomotor manipulation policies for humanoid robots, with a strong focus on real‑robot deployment. The role involves shaping research directions, leading development, and collaborating across perception, control, and hardware teams.

Key responsibilities

• Lead the design, implementation, and real‑world validation of learning‑based visuomotor policies for tasks such as grasping, object reorientation, bimanual manipulation, and assembly.
• Define research directions and technical roadmaps, advancing techniques like behavior cloning, reinforcement learning, and VLA‑based reasoning.
• Develop robust approaches to handle sensor noise, partial observability, contact dynamics, and environmental variability.
• Oversee the full research pipeline from data collection and model training to evaluation methodology and deployment on real robots.
• Manage project milestones, coordinate with collaborators, and supervise research associates, engineers, and PhD students.

Required profile

• PhD in Robotics, Computer Science, Electrical Engineering, or a related field.
• Strong publication record in robot learning, manipulation, embodied AI, or related venues (e.g., CoRL, RSS, ICRA, IROS, NeurIPS, CVPR).
• Demonstrated experience developing and deploying robot learning systems on real robots.
• Experience supervising or mentoring junior researchers or students.
• Ability to independently define research problems, design experiments, and drive projects to completion.

Required skills

• Python programming.
• Deep learning frameworks such as PyTorch.
• Behavior cloning and reinforcement learning for manipulation.
• Visuomotor control and robot manipulation techniques.