Embodied AI Robotics Scientist - Learning from Demonstration

A*STAR RESEARCH ENTITIES; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

A*STAR RESEARCH ENTITIES seeks a robotics scientist to advance Embodied AI for industrial robotics, focusing on Learning from Demonstration for contact-rich manipulation and skill acquisition. You will design experiments, collect demonstration data, and translate results into prototypes for real-world applications.

You will collaborate with multidisciplinary teams, apply deep learning techniques, and drive innovation in humanoid robotics capabilities for advanced manufacturing environments.

Qualifications

• PhD in Robotics, CS, EE or related field.
• Strong background in Embodied AI, Learning from Demonstration or related AI-driven robotics techniques.
• At least 2 years of experience.
• Knowledge of deep learning frameworks like TensorFlow and/or PyTorch.
• Proficiency in Python and C++.
• Hands-on experience with ROS2, simulation environments (Isaac Sim), and robotic hardware.
• Familiarity with industrial automation is an advantage.
• Strong communication skills for collaboration and presenting findings.

Responsibilities

• Conduct applied R&D in Embodied AI for robotics, focusing on LfD for contact-rich manipulation and skill acquisition.
• Design and execute experiments to collect, process, and analyse demonstration data for training robotic behaviours.
• Apply machine learning techniques, including deep learning, to improve robot control and decision-making.
• Translate research outcomes into functional prototypes and deployable robotics solutions for industry.
• Contribute to strategic development of Embodied AI and humanoid robotics capabilities.
• Leverage computer vision to enhance perception and object recognition where applicable.
• Research and implement state-of-the-art algorithms to improve performance and efficiency.
• Collaborate with hardware, software, and research teams to achieve project goals.
• Support stakeholder engagement and provide expert input on system capabilities and limitations.

Skills

Embodied AI

Learning from Demonstration

robot learning

deep learning

TensorFlow

PyTorch

Python

C++

ROS2

Isaac Sim

industrial automation

communication skills

Education

PhD in Robotics

PhD in Computer Science

PhD in Electrical Engineering

Tools

TensorFlow

PyTorch

ROS2

Isaac Sim

Job description

A*STAR RESEARCH ENTITIES seeks a robotics scientist to advance Embodied AI for industrial robotics, focusing on Learning from Demonstration for contact-rich manipulation and skill acquisition. You will design experiments, collect demonstration data, and translate results into prototypes for real-world applications.

You will collaborate with multidisciplinary teams, apply deep learning techniques, and drive innovation in humanoid robotics capabilities for advanced manufacturing environments.