Research Engineer (Dexterous in-hand manipulation)

National University of Singapore; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

National University of Singapore invites applications for a Research Engineer (Dexterous in-hand manipulation) within the College of Design and Engineering, Electrical and Computer Engineering, Kent Ridge Campus. The role focuses on developing real2sim2real learning and control methodologies to acquire robust dexterous manipulation skills in complex environments.

You will work on real-to-simulation modeling, simulation-based skill learning, and sim-to-real adaptation, using multimodal sensing to

Qualifications

• Master or Bachelor degree in robotics, CS, or electrical/ electronic engineering.
• Extensive experience in dexterous hand manipulation and real-world robotic applications.
• Proven experience with multi-fingered robotic systems and production-quality code.

Responsibilities

• Develop real2sim2real modeling and system identification for manipulation scenes.
• Design simulation-based learning and optimization for dexterous manipulation.
• Advance sim-to-real adaptation using multimodal sensing and feedback.

Skills

Dexterous hand manipulation

Real-world robotic applications

Multi-fingered robot systems

C++ and Python

Education

Master or Bachelor Degree in robotics/CS/EE

Tools

MuJoCo

ISSAC

Job description

Research Engineer (Dexterous in-hand manipulation)

University-Level Unit: College of Design and Engineering Faculty/Department-Level Unit: Electrical and Computer Engineering Employee Category: Research Staff Location: Kent Ridge Campus Posted On: 11/09/2026

Job Description

The research project focuses on developing real2sim2real learning and control methodologies for acquiring robust dexterous manipulation skills in complex, content-rich environments. The research engineer is expected to contribute to the following key aspects:
a) Develop real-to-simulation modeling and system identification methods that reconstruct manipulation scenes, object properties, contact dynamics, and robot–environment interactions from multimodal real-world observations, enabling high-fidelity and scalable simulation of dexterous manipulation tasks.

b) Design simulation-based skill learning and optimization methods for contact-rich dexterous manipulation, integrating differentiable simulation, trajectory optimization, reinforcement learning, and/or imitation learning to efficiently acquire transferable manipulation policies under complex physical constraints and diverse task conditions.

c) Develop sim-to-real adaptation and closed-loop skill refinement approaches that leverage multimodal sensory feedback, including vision, tactile, and proprioceptive information, to bridge the simulation-to-reality gap and continuously improve manipulation performance in the real world. The resulting real2sim2real framework will support scalable acquisition of generalizable dexterous manipulation skills and facilitate learning from rich human demonstrations, task semantics, and physical interactions for complex robotic manipulation scenarios.

Qualifications

• Master or Bachelor Degree in a relevant discipline, e.g. robotics, computer science, electrical/electronic engineering, etc.
• Extensive experience in dexterous hand manipulation, especially in in-hand skills with demonstrated expertise in real-world robotic applications.
• Substantial practical experience in real robot development and deployment, including multi-fingered robot systems.
• Proficient experience with various robotics simulators (e.g., MuJoCo, ISSAC) and excellent programming skills in C++ and Python with the ability to develop efficient, production-quality code.
• Open to Fixed Term Contract.

Req ID: 34392