Architected a full-stack visual classification platform using Flutter as the frontend framework and Flask as the backend REST API. The system allows users to upload and interact with visual content, which is then processed by AI models for classification and preference inference.

Developed computer vision pipelines and AI models for multi-label image classification and attribute extraction from visual datasets. The models were trained using PyTorch and integrated into the Flask backend for real-time inference.

Implemented inference logic for preference modeling based on historical interaction data and visual feature embeddings. The system learns user preferences over time by analyzing patterns in how users interact with classified content.

Designed a polyglot persistence layer with PostgreSQL for relational data, Redis for caching and session state, and MongoDB for unstructured logs and telemetry. This architecture ensures scalability and performance across different data access patterns.

Applied Scrum methodology adapted to a solo developer workflow with iterative planning and continuous integration, ensuring structured development and consistent delivery throughout the thesis project.

Flutter • Flask • PyTorch • Computer Vision • PostgreSQL • Redis • MongoDB • REST APIs • Scrum