🛠 Tech Stack

💼 About This Role

You'll build real-time 3D perception models for Zipline's autonomous drone delivery system, working across the full onboard perception stack. Your work will enable precise deliveries in diverse customer backyards worldwide. This role moves fast, shipping production-grade systems rather than pure research.

🎯 What You'll Do

• Implement, train and evaluate real-time 3D perception models
• Optimize models for onboard resource-constrained computers
• Build visualization, introspection and eval tooling
• Design data selection pipelines for valuable field data

📋 Requirements

• 5+ years building and deploying deep learning perception systems
• Strong understanding of classical computer vision fundamentals
• Expertise in robotics fundamentals (reference frames, SE(3) manifolds)
• Hands-on experience training and optimizing CNN/transformer architectures on target hardware

✨ Nice to Have

• Experience deploying models in real-world high-stakes robotics or autonomy applications
• Familiarity with building training, data annotation, and evaluation pipelines

🎁 Benefits & Perks

• 🚀 Autonomy to define roadmap and drive architectural decisions
• 🌍 Global impact with deliveries used thousands of times daily

📨 Hiring Process

Estimated timeline: 3-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Phone Screen· 60 min
3. 3Onsite Interviews· 4 hours