Your question is Microscopic Anomaly Detection Design. Take a moment with it on the right.
Talk me through your thinking if you like. When you're confident, submit your answer and I'll grade it like a real screen (7/10 or better passes).
How would you design a computer vision model to detect microscopic anomalies on a Micron Technology silicon wafer when you only have 50 examples of defective wafers and 100,000 examples of normal ones? You should address data splitting, augmentation, transfer learning, anomaly detection, class imbalance, threshold selection, and evaluation. Explain how you would prevent wafer or image-tile leakage and how the system would be monitored after deployment.