Amazon is looking for talented Postdoctoral Scientists to join our Amazon Robotics team for a one-year, full-time research position. Postdoctoral Scientists will innovate in key areas of machine learning, reinforcement learning, and foundational models for robotic manipulation.

The Postdoc will research, propose, and develop a generalizable robotic pick and pack policy by leveraging the state-of-the-art diffusion polices, data-efficient reinforcement learning methods, and foundation models for robotic perception and manipulation. The Postdoc will evaluate the performance of such a policy on at least two hardware platforms, and iteratively improve the performance on a variety of hardware configurations.

Key job responsibilities
• Research vision - Where should we be focusing our efforts in this rapidly developing field
• Research delivery – Proving/dis-proving strategies and methodologies, innovating and iterating ML solutions for robotic manipulation
• Research results - Publish your innovation in top-tier academic venues and hone your presentation skills.

A day in the life
• Be inspired by challenges and opportunities to invent cutting-edge techniques in your area(s) of expertise.
• Work closely with a senior science advisor, collaborate with other scientists and engineers, and be part of Amazon’s vibrant and diverse global science community.

About the team
The Manipulation Research Team aims to answer ambiguous open questions in the domain of robotic manipulation. We focus on generalizable machine learning models and multi-modalities in robotic grasping in order to impact a broad range of robotic manipulation applications across Amazon Fulfillment Network (AFN).