Applied Scientist II, Reinforcement Learning

Amazon; San Francisco (CA); On-site; USD 142,800 - 193,200; Full time

Benefits offered by this job

Comprehensive health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Amazon is seeking a robotics engineer to develop advanced robotics systems integrating AI and cutting-edge control methods. You will work on whole-body control, utilizing state-of-the-art techniques to enhance automation solutions. The position requires a PhD or Master’s degree with 2+ years in applied research, focusing on behaviors for diverse terrains. Join Amazon to pioneer robotics and help shape the future of automation. Full benefits included.

Qualifications

• PhD or Master’s degree with 2+ years of applied research experience.
• Experience with imitation learning and reinforcement learning.
• Knowledge of hierarchical quadratic programming and model‑predictive control.

Responsibilities

• Design and implement whole‐body control methods.
• Utilize state-of-the-art methods in control.
• Create robust behaviors for various terrains.

Skills

Imitation learning

Reinforcement learning

Real-time controllers

Behavior creation for terrains

Sensor fusion

Mentoring

Education

PhD or Master’s degree

Tools

IsaacLab

Mujoco

Drake

Java

C++

Python

Matlab

ROS

Job description

Amazon is seeking exceptional talent to help develop the next generation of advanced robotics systems that will transform automation at Amazon's scale. We are building revolutionary robotic systems that combine cutting‑edge AI, sophisticated control systems, and advanced mechanical design to create adaptable automation solutions capable of working safely alongside humans in dynamic environments. This unique opportunity allows you to shape the future of robotics and automation at an unprecedented scale, working with world‑class teams pushing the boundaries of robotics, locomotion, and human‑robot interaction. This role presents an opportunity to pioneer the application of deep learning and large language models in robotics.

Key Job Responsibilities

• Design and implement whole‑body control methods for balance, locomotion, and dexterous manipulation.
• Utilize state‑of‑the‑art methods in learned and model‑based control.
• Create robust and safe behaviors for different terrains and tasks.
• Implement real‑time controllers with stability guarantees.
• Collaborate effectively with multi‑disciplinary teams to co‑design hardware and algorithms for loco‑manipulation.
• Mentor junior engineers and scientists.

Basic Qualifications

• PhD or Master’s degree and 2+ years of applied research experience.
• Experience with imitation learning and reinforcement learning for whole‑body control.
• Experience with methods such as hierarchical quadratic programming and model‑predictive control.
• Experience with simulation environments such as IsaacLab, Mujoco, Drake, etc.
• Experience with developing and deploying code for real‑time controllers.
• Experience in state estimation from multiple sensor modalities.

Preferred Qualifications

• Experience programming in Java, C++, Python or related language.
• Experience working effectively across cross‑functional teams and partnering well with people at all levels within an organization.
• PhD in Robotics, with a focus on whole‑body control.
• Experience with low‑level joint torque/impedance control.
• Experience with teleoperation systems.
• Experience with robotics frameworks for fast prototyping (Matlab, ROS, etc.).

Benefits include comprehensive health insurance (medical, dental, vision, prescription), 401(k) matching, paid time off, parental leave, and other resources to support employee wellbeing.

USA, MA, Reading - 142,800.00 - 193,200.00 USD annually

Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.