Drimva

Amazon

Robotics/AI Motor Control Scientist, Fauna

$184K–$249K

New York, NY · Full-time · Posted Oct 6, 2026

Experience
3+ years of industry or academic research experience; PhD, or Master's degree and 6+ years of applied research experience.
Education
PhD, or Master's degree and 6+ years of applied research experience.

About the job

Develop and deploy AI-based robotic motor-control systems that enable robots to perform complex tasks safely and adaptively.

What you'll do

  • Develop and validate motor controllers using simulation and real-world testing.
  • Integrate control systems with robotic hardware and practical constraints, and lead projects through production deployment.
  • Mentor junior scientists and engineers and connect research with engineering implementation.

What they ask for

  • PhD, or Master's degree and 6+ years of applied research experience; also requires 3+ years of industry or academic research experience.
  • Experience in Java, C++, Python, or a related language, and experience leading technical initiatives and mentoring, leading, or managing junior engineers.
  • Strong publication record at major Robotics/ML/AI conferences; experience with robot-learning simulation environments and sim-to-real transfer.
  • Strong understanding of robotic kinematics and motion planning; experience applying reinforcement learning, imitation learning, or other AI techniques to robotic motor control.

Nice to have

  • Experience with PyTorch or JAX; impactful first-author publications or large-scale distributed RL training.
  • Technical leadership and cross-functional collaboration, research-to-production robotics, perception integration, or familiarity with hardware constraints and actuator dynamics.

Pay

183,800.00 - 248,700.00 USD annually (base salary)

Tools

Java, C++, Python, Isaac Gym/Lab, MuJoCo, PyTorch, JAX

AI focus

Developing motor-control algorithms using reinforcement learning, imitation learning, and other AI techniques; includes robot learning, sim-to-real transfer, and potentially distributed RL training.

Model-written summary · the original posting is authoritative

First seen Oct 15, 2026 · Last verified Nov 6, 2026 (UTC)