Embodied AI Robotics Engineer — Real-World Humanoids

YY circle; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

YY circle seeks an hands-on Embodied AI Engineer to develop and deploy robot learning on physical humanoid robots. You will own data collection, model training, and validation from lab to real-robot environments, balancing research with practical deployment.

The role spans AI development, robot integration, data collection, testing, and iterative performance improvement across simulation and real-world scenarios.

Qualifications

• Master’s degree or higher in Robotics, CS, AI, or a related field.
• Willingness to work across AI, robotics, hardware, data collection, testing, and operations.
• Hands-on experience with robotic systems, including integration, calibration, or teleoperation.
• Good knowledge of VLA models, imitation learning, RL, or diffusion policies.

Responsibilities

• Develop, integrate, and fine-tune robot foundation models for perception, mapping, task planning, and embodied decision-making.
• Own the development cycle from data collection and model training to physical-robot deployment and validation.
• Test and analyze system failures, then improve performance through targeted data collection, model retraining, and iterative validation in both simulation and real-world environments.
• Track key performance metrics, including task success rate, completion time, intervention rate, repeatability, and safety.

Skills

VLA models

Imitation learning

Reinforcement learning

Diffusion policies

Robotic systems

Data collection

Education

Master’s degree or above

Tools

Cloud GPU infrastructure

Job description

YY circle seeks an hands-on Embodied AI Engineer to develop and deploy robot learning on physical humanoid robots. You will own data collection, model training, and validation from lab to real-robot environments, balancing research with practical deployment.

The role spans AI development, robot integration, data collection, testing, and iterative performance improvement across simulation and real-world scenarios.