Applied Scientist, Robotic Motion & Learning

Amazon Science; Seattle (WA); On-site; USD 143,000 - 193,000; Full time

Benefits offered by this job

Full medical/dental/vision

RSUs

401(k) with match

Paid time off

Job summary

Amazon Robotics seeks an Applied Scientist to join the Motion Behaviors team. You will drive the development of learned controllers and behavior for manipulation on production robots, applying reinforcement learning and imitation learning in complex environments.

You will design policies, run simulations, and deploy reliable real-time solutions while collaborating across disciplines and sharing insights through publications and talks.

Qualifications

• PhD or Master’s degree in a related field with 4+ years of experience.
• Experience programming in Java, C++, Python or related language.
• Experience in patents or publications at top-tier conferences/journals.
• Experience training reinforcement learning or imitation learning policies for manipulation or robot control problems.
• Strong background in reinforcement learning and scalable training in simulation.

Responsibilities

• Develop learned controllers and manipulation behaviors from research prototypes through deployment on production robots.
• Research, design, and implement motion planning, control, and decision-making algorithms to improve system performance.
• Design and deploy learning pipelines that transfer policies from simulation to real-time execution on robots.
• Develop models to predict manipulation outcomes and inform behavior selection under uncertainty.
• Leverage operational data to identify failure modes and drive policy improvements.
• Represent Amazon in academia through publications and presentations.

Skills

Java

C++

Python

Reinforcement Learning

Imitation Learning

Publications/Patents

Education

PhD or Master’s degree with 4+ years of experience

Job description

Amazon Robotics seeks an Applied Scientist to join the Motion Behaviors team. You will drive the development of learned controllers and behavior for manipulation on production robots, applying reinforcement learning and imitation learning in complex environments.

You will design policies, run simulations, and deploy reliable real-time solutions while collaborating across disciplines and sharing insights through publications and talks.