- Developed Python scripts leveraging YOLOv9 for object detection in large-scale video datasets on AWS - Applied RetinaFace for face detection across video frames, logging bounding boxes, frame numbers, and accuracy metrics- Engineered a parser to extract a refined dataset (7M videos) from a larger 70M video corpus for data fine-tuning- Utilized WebUI and ComfyUI to generate live videos from images, facilitating comparison with custom SVD models- Streamlined data processing pipelines by organizing team datasets on AWS

- Assisted in lab sections, helped students on homework and debug their programs. - Strengthened students' understanding of fundamental CS topics including recursion, abstraction, trees, OOP, linked lists and efficiency.