Key Responsibilities:

• Research & Development of machine learning algorithms for telemanipulation, contact rich dexterous manipulation, object pose estimation and operator intention estimation.
• Implementing the algorithms in simulation and verify on multi-fingered teleoperation avatar robot hardware.
• Research topics may include the application of machine learning to human intention modeling, interaction planning, dexterous skills acquisition, contact-rich manipulation policy learning, learning from videos, reducing sim-to-real gap, and various related technologies.
• Collaborate with local and international researchers and engineers within the company.
• File patents on developed technologies.
• Publish the research results at top-tier conferences and journals in machine learning and robotics.

Minimum Qualifications:

• Ph.D. in computer science, robotics, mechanical engineering, electrical engineering, or a related field.
• Experience with robotic manipulation, control, and dynamics.
• Experience with  machine learning deployed on a real robotics platform.
• Familiarity with deep learning platforms such as TensorFlow and PyTorch.
• Good programming skills in C++ or Python.
• Familiarity with robot hardware and proficient in using ROS.
• Strong written and oral communication skills.

Bonus Qualifications:

• Experience in robotic teleoperation and collaborative robotic development
• Experience in robotic object pose estimation and perception system development.
• Experience with simulation platforms and engines, such as MuJoCo, PyBullet, IsaacSym, IsaacGym, Unreal Engine.
• Experience with building simulated environments and training manipulation policies in simulation and transfer to real (sim-to-real)
• Experience with policy deployment on multi-fingered robots and/or contact-rich tasks.
• Experience in human action and task recognition using multimodal data.
• Experience in frameworks and methodologies utilized in building LLM, LVM, and LMM applications.

Years of Experience Required:  2-5 years