🛠 Tech Stack

💼 About This Role

You'll develop Vision-Language-Action (VLA) models for Amazon's fleet of delivery robots, leveraging real-world robotic data to enhance autonomy and navigation. Your work will directly impact last-mile delivery at scale, blending AI with real hardware.

🎯 What You'll Do

• Develop and implement VLA models and imitation learning algorithms
• Design and test algorithms for real-world autonomy and navigation
• Streamline data collection and training workflows
• Optimize networks for real-time edge deployment

📋 Requirements

• Master's in Engineering, Robotics, or Machine Learning
• 3+ years industry or research experience
• Strong deep learning fundamentals (Transformers, diffusion models)
• Experience with VLA models or generalist robot models (e.g., RT-2)

✨ Nice to Have

• PhD in Robotics or related field
• Publications at top-tier conferences
• Production-level C++ skills

🎁 Benefits & Perks

• 🏖️ Unlimited PTO
• 🏥 Health insurance
• 💻 Remote flexibility
• 🚗 Commuter benefits
• 🍱 Free lunch

🚩 Heads Up

• Mentions leading a team but only requires 3 years experience