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

About the role

Our organization in Amazon Robotics builds robots that perform contact-rich manipulation safely and reliably in complex, unstructured environments, at Amazon scale. We learn from real-world data at a scale that few teams in robotics can access. As a Senior Applied Scientist, you will guide a small team advancing reinforcement learning for manipulation, creating robots that learn to push, flip, rearrange, and dexterously insert items with unparalleled robustness, speed, and reliability. The goal is to deploy robots across Amazon's global network capable of handling the full diversity of items Amazon sells. You will set the technical direction for learning these behaviors, from simulation training to execution on physical robots, and demonstrate new manipulation capabilities on real hardware at scale. This team's mission extends beyond any single product, aiming to invent and apply manipulation capabilities that generalize to many future robotics applications.

Responsibilities

• Set the technical direction for learning non-prehensile and contact-rich manipulation policies, from testing advances in the field to demonstrating capability on hardware.
• Oversee the development of reinforcement learning approaches addressing the long tail of diverse, demanding manipulation conditions.
• Own the path from simulation training to reliable, real-time execution on physical robots, making evidence-based decisions on where learned approaches should replace engineered ones.
• Demonstrate new manipulation capabilities on real robots at scale, turning one-off results into repeatable methods.
• Establish standards, evaluation practices, and data-informed improvement loops for the team.
• Mentor scientists and engineers, raising the bar for applied science rigor and engineering quality.
• Partner across control, perception, and hardware teams to integrate learned behaviors into working systems.
• Represent Amazon in academia through publications and scientific presentations.

Requirements

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

Preferred Qualifications

• Experience with sim-to-real transfer at scale (domain randomization, system identification, etc.).
• Experience designing reward functions and training curricula for reinforcement learning on robotic systems.
• Experience with contact-rich or non-prehensile manipulation, including extrinsic dexterity and force/torque control.
• Publications in top robotics or machine learning venues (RSS, CoRL, ICRA, NeurIPS, ICML, etc.).

Benefits

Amazon offers a full range of benefits supporting you and eligible family members, including domestic partners. Benefits can vary by location, hours worked, length of employment, and job status. Generally, full-time employees receive:

• Medical, dental, and vision coverage.
• Maternity and parental leave options.
• Paid time off (PTO).
• 401(k) plan.

Pay

Base salary range: $167,100 - $226,100 USD annually (USA, WA, Seattle). Your compensation package will include sign-on payments and restricted stock units (RSUs). Final compensation is determined based on experience, qualifications, and location.