RL Robotics Engineer: Manipulation & Real-World AI Systems

Amazon Inc.; Zürich; Presencial; CHF 150.000 - 200.000; Jornada completa

Descripción de la vacante

Amazon is seeking an Applied Scientist to advance intelligent robotic manipulation systems powered by reinforcement learning. You will research, design, and deploy ML solutions enabling robots to interact with the physical world, tackling ambiguous problems and inventing new approaches.

You will see research deployed on real hardware at scale. You will collaborate across teams to validate simulation requirements, refine models with hardware feedback, and mentor others while contributing to a

Formación

• Master's degree or higher in Engineering, Robotics, or Machine Learning.
• A minimum of five years of industry or research experience, with PhD experience applicable.
• Strong deep learning fundamentals, including supervised and self-supervised learning techniques, and reinforcement learning, MDPS, neural networks, policy optimization, and sim-to-real transfer.
• Strong background in robotics including autonomy and/or manipulation.
• Experience with deploying neural networks on hardware platforms.
• Ability to write production-level code in modern C++.
• Ability to prototype algorithms and train deep neural networks in Python.
• Strong background in robotic manipulation, including dynamics, grasp synthesis, and trajectory optimization.

Responsabilidades

• Research and develop reinforcement learning methods for robotic manipulation, advancing sim-to-real transfer, contact-rich control, and adaptive grasping.
• Design, implement, and evaluate ML models using PyTorch or TensorFlow to train policies that generalize across manipulation tasks.
• Build and maintain production-quality code integrating prototypes into robotics systems, balancing complexity, performance, and maintainability.
• Collaborate with cross-functional teams to define simulation requirements, validate model performance, and iterate using real-world hardware feedback.
• Contribute to scientific roadmap by identifying new directions, mentoring scientists, and publishing results when appropriate.

Conocimientos

Reinforcement learning

Robotics manipulation

Python

C++ production code

Educación

Master's degree in Engineering/ML

PhD advantageous

Herramientas

PyTorch

TensorFlow

Descripción del empleo

Amazon is seeking an Applied Scientist to advance intelligent robotic manipulation systems powered by reinforcement learning. You will research, design, and deploy ML solutions enabling robots to interact with the physical world, tackling ambiguous problems and inventing new approaches.

You will see research deployed on real hardware at scale. You will collaborate across teams to validate simulation requirements, refine models with hardware feedback, and mentor others while contributing to a