Visuomotor Robotics Research Fellow (Real-Robot Deployment)

Nanyang Technological University Singapore; Singapore; On-site; SGD 78,000 - 100,000; Full time

Job summary

NTU's SHARE@NTU Corporate Laboratory in Singapore invites a Research Fellow with a strong robotics learning background to develop visuomotor manipulation policies for humanoid robots and to deploy them on real robots.

You will lead research, shape roadmaps for grasping, reorientation, and bimanual tasks, advance learning methods such as behavior cloning and RL, and oversee data collection, model training, evaluation, and deployment while collaborating with perception, controls, and hardware

Qualifications

• PhD in Robotics, Computer Science, Electrical Engineering, or a related field.
• Strong publication record in robot learning, manipulation, embodied AI, or related areas (e.g., CoRL, RSS, ICRA, IROS, NeurIPS, CVPR).
• Demonstrated experience developing and deploying robot learning systems on real robots.
• Deep expertise in robot manipulation and visuomotor control.
• Strong command of behavior cloning, reinforcement learning, or related learning-based manipulation methods.
• Proficiency in Python and modern deep learning frameworks (e.g., PyTorch).
• Proven ability to independently define research problems, design experiments, and drive projects to completion.
• Experience supervising or mentoring junior researchers or students.

Responsibilities

• Lead the research and development of learning-based visuomotor policies for humanoid robot manipulation, from problem formulation to real-world validation.
• Define research directions and technical roadmaps for manipulation capabilities such as grasping, object reorientation, bimanual manipulation, and assembly.
• Advance techniques including behavior cloning, reinforcement learning, and RL-based reasoning, with a focus on publishable outcomes.
• Develop robust approaches to sensor noise, partial observability, and environment variability.
• Oversee the research pipeline from data collection strategy and model training to evaluation methodology and deployment.
• Manage project milestones, deliverables, and timelines; coordinate with collaborators and stakeholders, and report progress to the PI.
• Supervise and mentor research associates, engineers, and PhD students working on the project.
• Collaborate with perception, controls, systems, and hardware teams to guide integration of learned policies into the full autonomy stack.
• Evaluate tradeoffs between learning-based and classical approaches and make principled architectural and design decisions.
• Lead the preparation of publications, technical reports, and grant/project documentation.

Skills

Robot learning

Visuomotor control

Python

PyTorch

Reinforcement learning

Behavior cloning

Mentoring

Project leadership

Education

PhD in Robotics / CS / EE

Tools

Python

PyTorch

ROS

Job description

NTU's SHARE@NTU Corporate Laboratory in Singapore invites a Research Fellow with a strong robotics learning background to develop visuomotor manipulation policies for humanoid robots and to deploy them on real robots.

You will lead research, shape roadmaps for grasping, reorientation, and bimanual tasks, advance learning methods such as behavior cloning and RL, and oversee data collection, model training, evaluation, and deployment while collaborating with perception, controls, and hardware