Research Fellow (Robot Learning & Manipulation)

SHARE@NTU Corporate Laboratory focuses on the development of key technologies for humanoid robotics, aimed at enabling intelligent services, industrial assistance, and human-centric applications. The research areas include multimodal sensing, artificial intelligence, environmental perception and situational awareness, as well as real-time motion planning and decision-making, allowing humanoid robots to operate safely and efficiently in complex and dynamic environments. Through the development of advanced humanoid robotic platforms, SHARE@NTU Lab seeks to address the growing global demand for automation while cultivating the next generation of local talent in robotics, artificial intelligence, and intelligent sensing technologies.

Our Lab aims to hire a Research Fellow with strong robotics learning background to help develop and improve our visuomotor manipulation policies, with a heavy emphasis on real-robot deployment.

Key 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 VLA-based reasoning, with a focus on novel contributions and publishable outcomes

Develop principled approaches to robustness challenges such as sensor noise, partial observability, contact dynamics, 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

Job Requirements:

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

Bonus Qualifications

Prior work on humanoids or highly dexterous robotic platforms

Experience transitioning research prototypes into commercial or production robotic systems

Track record of successful collaboration with industry partners

Passion for building autonomous humanoid robots that operate in the real world

We regret that only shortlisted candidates will be notified.

Hiring Institution: NTU