Visuomotor Robot Learning & Manipulation Associate

Nanyang Technological University Singapore; Singapore; On-site; SGD 70,000 - 110,000; Full time

Job summary

Nanyang Technological University Singapore's SHARE@NTU Corporate Laboratory seeks a Research Associate with a strong robotics learning background to develop and improve visuomotor manipulation policies for humanoid robots, with emphasis on real-robot deployment.

You will design and train policies, deploy on real hardware, collaborate with perception, controls, and hardware teams, and ensure robust performance from data collection to deployment.

Qualifications

• Master's degree in Robotics, CS, or EE.
• Hands-on experience deploying robot learning systems on real robots.
• Strong background in robot manipulation and visuomotor control.
• Experience with behavior cloning or reinforcement learning methods.
• Proficiency in Python and/or C++ for robotics and ML systems.

Responsibilities

• Design, train, evaluate, and deploy learning-based visuomotor policies for humanoid robot manipulation.
• Develop manipulation behaviors such as grasping, pick-and-place, object reorientation, door opening, and bimanual manipulation.
• Collaborate with perception, controls, systems, and hardware teams to integrate policies into a full autonomy stack.
• Write high-quality, well-tested software that ships to and runs on physical humanoid robots.
• Own the full pipeline from data collection on real robots to model training, evaluation, and deployment.

Skills

Robotics

Visuomotor control

Reinforcement learning

Behavior cloning

Python

C++

PyTorch

Experiment design

Education

Master's degree in Robotics, Computer Science, Electrical Engineering

Tools

ROS

Job description

Nanyang Technological University Singapore's SHARE@NTU Corporate Laboratory seeks a Research Associate with a strong robotics learning background to develop and improve visuomotor manipulation policies for humanoid robots, with emphasis on real-robot deployment.

You will design and train policies, deploy on real hardware, collaborate with perception, controls, and hardware teams, and ensure robust performance from data collection to deployment.