Robotics AI Engineer — Vision-Language & Autonomy

Amazon Inc.; Seattle, Northern (WA, KY); Hybrid; USD 180,000 - 220,000; Full time

Job summary

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. You will develop multi-modal models enabling robots to generate actions from demonstrations, sensor data, and natural language commands.

We seek an expert in VLA models, imitation learning, and generative AI with deep knowledge of supervised and self-supervised learning. Join us in shaping the future of intelligent robotics and real-world autonomy.

Qualifications

• PhD experience applicable to the role.
• Hands-on experience with Vision-Language-Action models or large-scale robot models.

Responsibilities

• Develop and implement Vision-Language-Action (VLA) models, generalist robot transformers, and imitation learning algorithms to enable robots to autonomously execute complex tasks.
• Design, test, and refine algorithms for real-world autonomy and navigation with focus on spatial reasoning and generalization.
• Streamline data collection and training workflows to expand model capabilities.
• Collaborate with the reinforcement learning team to leverage simulated and real-world data.
• Optimize and distill networks for real-time edge deployment (e.g., Nvidia Jetson Thor).
• Build, lead and mentor an exceptional software engineering team.
• Provide expert guidance to product managers and executives for strategic decisions.
• Create and maintain documentation, guidelines, and best practices.

Skills

Deep learning

Transformer models

Imitation learning

Generative AI

Supervised learning

Self-supervised learning

Python PyTorch

Robotics autonomy

Education

Master's degree or higher

PhD preferred

PhD experience applicable

Tools

C++ production

Job description

RIVR, an Amazon company, is building Physical AI by deploying autonomous robots for real-world doorstep delivery. You will develop multi-modal models enabling robots to generate actions from demonstrations, sensor data, and natural language commands.

We seek an expert in VLA models, imitation learning, and generative AI with deep knowledge of supervised and self-supervised learning. Join us in shaping the future of intelligent robotics and real-world autonomy.