Robotics AI Engineer — Vision-Language-Action & Autonomy

Amazon Inc.; Zürich; Híbrido; CHF 150.000 - 230.000; Jornada completa

Descripción de la vacante

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. We seek an expert in Vision-Language-Action models, imitation learning, and generative AI to develop multi-modal models enabling robots to act from demonstrations and sensor data.

You will collaborate with the reinforcement learning team, optimize for edge deployment on Nvidia Jetson Thor, mentor engineers, and contribute to product strategy while documenting best practices.

Formación

• PhD-level or equivalent research experience preferred.
• Proven experience with Vision-Language-Action models or large-scale generalist robot models.
• Strong robotics background including autonomy and navigation.
• Experience deploying neural networks on hardware platforms.
• Proficiency in Python (PyTorch) for prototyping and training.
• Production-level coding ability in modern C++.

Responsabilidades

• Develop and implement Vision-Language-Action models and robot transformers.
• Design, test, and refine algorithms for real-world autonomy and navigation tasks.
• Streamline data collection and training workflows for new tasks and data sources.
• Collaborate with RL teams to leverage simulated and real-world data.
• Optimize and distill networks for edge deployment (e.g. Nvidia Jetson Thor).
• Build and mentor a team of software engineers.
• Provide guidance to product managers and executives.
• Create and maintain documentation and best practices.

Conocimientos

Deep learning

Transformer architectures

Imitation learning

Diffusion models

Python (PyTorch)

Educación

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

PhD preferred

Herramientas

C++

Python

Nvidia Jetson Thor

Descripción del empleo

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. We seek an expert in Vision-Language-Action models, imitation learning, and generative AI to develop multi-modal models enabling robots to act from demonstrations and sensor data.

You will collaborate with the reinforcement learning team, optimize for edge deployment on Nvidia Jetson Thor, mentor engineers, and contribute to product strategy while documenting best practices.