Responsibilities

• Develop and deploy manipulation policies for dexterous task execution on physical robots
• Build grasp planning and contact-rich control pipelines that generalize across varied objects and environments
• Design and run data collection and teleoperation infrastructure to feed policy training at scale
• Train manipulation policies using imitation learning, reinforcement learning, or hybrid approaches
• Integrate manipulation with the perception stack and broader autonomy pipeline
• Diagnose failure modes on hardware systematically and drive improvements

Requirements

• Strong foundations in robotics, control theory, and motion planning
• Hands-on experience with manipulation systems on real robotic platforms, gained through industry or research work
• Proficient in Python and C++, with PyTorch or JAX experience
• Experience taking manipulation work from prototype to hardware deployment
• Exposure to data collection or teleoperation workflows for policy training
• Candidates with limited industry experience are welcome to apply, provided this is supported by strong relevant academic or research work, such as a thesis, publications, or hands-on robotics projects

Tyson Jay Management Pte Ltd | EA License No.: 24C2479 

Ivan Lim | EA Personnel No.: R1109856