Robotics Scientist II: Whole-Body Control & Dexterous AI

Amazon Science; Massachusetts; On-site; USD 143,000 - 193,000; Full time

Job summary

Amazon Science in Massachusetts is seeking a research engineer to advance robotics systems integrating AI, ML, control, and mechanical design for dexterous manipulation and locomotion. You will work on real-time controllers and safe, adaptive behavior across dynamic environments, mentoring teammates along the way.

The role blends deep learning with practical robotics, partnering across hardware and software teams to push the boundaries of human-robot interaction at scale.

Qualifications

• PhD or Master’s degree with 2+ years in CS/CE/ML or related field.
• Experience with imitation and reinforcement learning for whole-body control.
• Experience with HQP and MPC methods.
• Experience with simulation environments (IsaacLab, MuJoCo, Drake).
• Experience deploying code for real-time controllers.
• Experience with state estimation from multiple sensors.

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 with multi-disciplinary teams to co-design hardware and algorithms for loco-manipulation.
• Mentor junior engineers and scientists.

Skills

Imitation learning

Reinforcement learning

Hierarchical Quadratic Programming

Model Predictive Control

Simulation environments

Real-time control

Sensor fusion

Java

C++

Python

Collaboration

Impedance control

Teleoperation

MATLAB

ROS

Education

PhD, or Master’s degree in CS/CE/ML or related field

PhD in Robotics

Tools

IsaacLab

MuJoCo

Drake

ROS

Matlab

Job description

Amazon Science in Massachusetts is seeking a research engineer to advance robotics systems integrating AI, ML, control, and mechanical design for dexterous manipulation and locomotion. You will work on real-time controllers and safe, adaptive behavior across dynamic environments, mentoring teammates along the way.

The role blends deep learning with practical robotics, partnering across hardware and software teams to push the boundaries of human-robot interaction at scale.