Where AI meets physical machines
See what we teach →A platform built around one specific gap
Drribtex started in 2017 with a pretty narrow focus: most robotics courses taught either hardware or software in isolation. Nobody was teaching how modern AI actually gets deployed on physical robotic systems — the messy, real-world version where latency, sensor noise, and compute constraints matter.
So we built a curriculum around that gap. Each masterclass is led by practitioners who work on production systems, not researchers presenting theoretical models. The content is dense by design — participants need a baseline in either ML or robotics before joining most tracks.
Students come from over 40 countries. Some are engineers pivoting into AI. Some are robotics specialists who want to understand what their software colleagues are actually doing. The mix makes the learning environment unusually honest about what's hard.
The people behind the curriculum
Each instructor brings active field experience — not just academic credentials. The table here shows the core team and what they actually cover, so you know exactly who you're learning from before you commit to a track.
| Name | Domain focus |
|---|---|
| Oren Szabo | Lead AI Systems Instructor Reinforcement learning for autonomous navigation; previously built control systems for industrial arms. |
| Nadia Ferreira | Robotics Engineering Specialist Sensor fusion and real-time perception pipelines; ROS2, SLAM, and embedded inference. |
| Taavi Leppänen | Computer Vision Lead Object detection and depth estimation on edge hardware; edge deployment with ONNX and TensorRT. |
| Miriam Osei | Curriculum Designer Structures each track for working professionals — pacing, prerequisites, and assessment design. |
| Rafi Katz | Systems Integration Instructor Hardware-software co-design; focuses on the gap between prototype behavior and production reliability. |