I’m running a real-world industrial project that needs an advanced intern who can turn Python, OpenCV and solid machine-learning knowledge into a fully working, camera-driven inspection station for printed-circuit boards. The goal is straightforward: from a live feed you will detect wrong resistor values via colour-code reading, spot diode mis-orientation, and flag capacitor polarity errors. Your daily focus will be real-time camera feed processing. That means writing latency-aware OpenCV pipelines, integrating YOLO (or a comparable object-detection network), and pushing frames through a decision layer that raises on-screen alerts and overlays bounding boxes when something is off. You’ll also help with camera calibration, dataset curation and model training so the system improves as new boards come down the line. Deliverables I’ll review for acceptance: • A Python repository with documented code that builds and runs cross-platform • A trained model (weights + config) ready for inference on 30 fps feeds • Calibration scripts and a small, well-labelled image set for reproducibility • Demo video—or live session—showing correct detection of resistors, diodes and capacitors with on-screen marking and audible/visual alerts If advanced-level computer-vision work excites you and you’re comfortable moving fast from prototype to production, you’ll fit perfectly.