Senior Applied Scientist - Manipulation RL, Amazon Robotics - Vulcan Stow

What you'll do

• Set technical direction and oversee development of manipulation policies, including their evaluation and transfer from simulation to robots.
• Demonstrate capabilities on real hardware at scale; establish evaluation and improvement practices, and integrate learned behaviors with control, perception, and hardware teams.
• Mentor scientists and engineers, maintain scientific and engineering standards, and represent Amazon through publications and presentations.

What they ask for

• PhD or equivalent research experience.
• 7+ years of applied research experience; 3+ years building machine learning models for business application.
• Experience programming in Java, C++, Python or a related language; 3+ years building and deploying learning-based control on robotic systems.
• Track record training reinforcement learning or imitation learning policies in simulation and transferring them to physical systems; experience leading technical projects and mentoring scientists or engineers.

Nice to have

• Experience with sim-to-real transfer at scale, reward functions and training curricula for robotic reinforcement learning, or contact-rich/non-prehensile manipulation.
• Publications in top robotics or machine learning venues (RSS, CoRL, ICRA, NeurIPS, ICML, etc.).

Pay

167,100.00 - 226,100.00 USD annually (base salary)

Tools

Java, C++, Python

AI focus

Reinforcement and imitation learning for robotic manipulation, including training in simulation, sim-to-real transfer, and deployment of learned control policies on physical robots.