• Conduct exploratory research and experimentation on AI, CV, and NLP approaches • Develop Python-based solutions using OpenCV, YOLO, and similar technologies • Build and validate strategies to improve intelligent document processing workflows • Support experiments to optimize accuracy, performance, and scalability of detection models • Develop OpenCV algorithms to detect structural layout components in common medical charts • Build and refine YOLO-based detection models for medical chart elements (e.g., sections, tables) and measure accuracy • Document findings and contribute to technical discussions on model improvements