Embodied AI Scientist: Humanoid Actuation and Learning

A*STAR RESEARCH ENTITIES; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

A*STAR RESEARCH ENTITIES invites applications for an Embodied AI Scientist to advance actuator-centric embodied intelligence in humanoid robotics. You will develop learning-enabled control and decision-making methods tightly coupled with actuators, sensing and motion dynamics, joining robotics, AI and mechatronics.

The role covers experimental validation with joint modules and testbeds, integration of mechanical transmissions, and deployment of reinforcement learning for energy-efficient, safe

Qualifications

• PhD required in a relevant engineering field.
• Experience in humanoid robotics or actuated systems is preferred.
• Proficiency in programming and numerical tools.

Responsibilities

• Research embodied AI methods for humanoid robots focusing on actuation and control.
• Develop learning- and model-based control accounting for actuator dynamics.
• Integrate multi-modal sensing and reinforcement learning in control loops.
• Contribute to safe, constrained learning for locomotion and manipulation.
• Lead experimental studies on humanoid joint modules and testbeds.

Skills

Actuated robotics

C/C++

Python

MATLAB

Reinforcement learning

Control systems

Machine learning

Experimentation

Team collaboration

Education

Ph.D. in Mechanical, Electrical, Control or Mechatronics Engineering

Tools

Ansys Maxwell

Comsol Multiphysics

JMAG

Job description

A*STAR RESEARCH ENTITIES invites applications for an Embodied AI Scientist to advance actuator-centric embodied intelligence in humanoid robotics. You will develop learning-enabled control and decision-making methods tightly coupled with actuators, sensing and motion dynamics, joining robotics, AI and mechatronics.

The role covers experimental validation with joint modules and testbeds, integration of mechanical transmissions, and deployment of reinforcement learning for energy-efficient, safe