An end-to-end encrypted, real-time messaging web application. Messages are encrypted client-side using AES-256-GCM with RSA-4096 key exchange, ensuring that only intended recipients can read them. The app supports real-time messaging via WebSockets and persists message history in PostgreSQL.
Compared feedforward and bidirectional GRU architectures for identifying individuals from body pose sequences using the PoseTrack21 dataset. Automated hyperparameter tuning with Optuna on NVIDIA H100 GPU nodes via the University of Sheffield HPC cluster. Augmented training sequences using a sliding window approach and evaluated models with top-1 accuracy, calibration metrics, and occlusion-based ablation tests.
As part of a team project with the University of Sheffield AMRC, developed an online workplace training platform in Ruby on Rails. The application allows businesses to create, manage, and assign training courses to employees. Worked with a non-technical client in weekly agile sprints to extract requirements, demo progress, and iteratively refine features.