During the technical interview, the interviewer focused mainly on my project that used YOLOv8 for food detection. I was first asked to explain the overall workflow of YOLO, where I described how the image passes through the backbone for feature extraction, the neck for feature fusion, and the detection head for predicting bounding boxes and class labels. They specifically asked what “single forward pass” means, and I explained that YOLO processes the entire image only once to detect all objects simultaneously, unlike traditional methods that scan regions multiple times. I was also asked why I chose YOLOv8 over older YOLO versions, where I highlighted its anchor-free design, better accuracy–speed tradeoff, and easier integration. The interviewer then compared YOLO with CNNs, and I clarified that CNNs are mainly used for image classification, whereas YOLO performs object detection by identifying both the object and its location. Overall, the discussion was practical and project-oriented rather than purely theoretical, and the interviewer seemed satisfied with my clear explanations and understanding of real-world usage.