Senior AI Engineer: Robotic Manipulation & RL

Amazon Inc.; Asti; On-site; EUR 90,000 - 130,000; Full time

Job summary

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. We seek a Senior AI Engineer with deep expertise in reinforcement learning and deep learning, focusing on dexterous manipulation, using both simulated and real-world data to tackle dynamic grasping and object interaction.

Join us to advance intelligent robotics, collaborate across teams, and contribute production-grade code in C++ and Python to push the boundaries of embodied AI.

Qualifications

• Master’s degree or higher in a relevant field (Engineering, Robotics or Machine Learning).
• 5+ years of industry or research experience, PhD experience applicable.
• Strong deep learning fundamentals including supervised and self-supervised learning, RL (MDPs, policy optimization, model-based vs model-free).
• Robotics background with autonomy/manipulation and deployment of neural nets on hardware.

Responsibilities

• Develop cutting-edge reinforcement learning algorithms for dexterous manipulation combining vision, depth, tactile, and proprioceptive data.
• Design, test and refine algorithms for real-world manipulation challenges like diverse packages, door handles, and dynamic hand-offs.
• Collaborate with the foundation model team to leverage simulated and real-world data.

Skills

Reinforcement learning

Robotics manipulation

Neural networks

Python

C++

MDP & RL theory

Education

Master’s degree or higher in Engineering/Robotics/Machine Learning

Tools

Python

C++

Job description

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. We seek a Senior AI Engineer with deep expertise in reinforcement learning and deep learning, focusing on dexterous manipulation, using both simulated and real-world data to tackle dynamic grasping and object interaction.

Join us to advance intelligent robotics, collaborate across teams, and contribute production-grade code in C++ and Python to push the boundaries of embodied AI.