Applied Scientist - Amazon Robotics, Amazon Robotics - Vulcan Stow

What you'll do

• Develop learned controllers and manipulation behaviors from research prototypes through production deployment.
• Design motion-planning, control, decision-making, and learning pipelines for reliable real-time robot execution.
• Use operational data to identify failure modes and improve policies; publish and present scientific work.

What they ask for

• PhD, or Master's degree and 4+ years of science, technology, engineering or related field experience
• Experience programming in Java, C++, Python or related language
• Experience in patents or publications at top-tier peer-reviewed conferences or journals
• Experience training reinforcement learning or imitation learning policies for manipulation or robot control problems; strong background in reinforcement learning, including reward design and training at scale in simulation

Nice to have

• Experience in professional software development
• Experience with sim-to-real transfer or familiarity with learned dynamics or world models for manipulation

Pay

142,800.00 - 193,200.00 USD annually (base salary)

Tools

Java, C++, Python

AI focus

Apply reinforcement learning and behavior cloning/imitation learning to robot manipulation, including training policies in simulation, transferring them to physical robots, and predicting outcomes to select behaviors under uncertainty.