Ravelos

• Developed intermittent demand forecasting systems for retail-like datasets containing 20K+ products, 3M+ rows, and approximately 85% zero-demand observations.
• Designed a two-stage forecasting architecture using classification and LightGBM-based regression pipelines for sparse demand modeling.
• Built fully recursive inference workflows where future predictions were generated without access to unavailable future information, preventing data leakage.
• Improved forecasting accuracy from approximately 40% to 65-70% using custom business-oriented evaluation metrics and advanced feature engineering.
• Reduced end-to-end ML pipeline runtime from 40 minutes to 4 minutes through vectorization, parallelization, memory optimization, and matrix-based computation.

Vcamp

• Developed UAV-oriented autonomous perception systems using hybrid visual odometry architectures.
• Combined classical computer vision techniques including ORB and optical flow with RAFT-based deep learning motion estimation pipelines.
• Designed confidence-aware model arbitration mechanisms for dynamically selecting the most reliable motion estimation outputs.
• Performed real-time experimentation on custom drone footage with approximately 7.5 FPS inference performance using PyTorch and OpenCV.

Spaidream

• Built SketchMind, an AI-powered storytelling and social interaction platform for children using Flutter, Firebase, and OpenAI APIs.
• Developed end-to-end mobile AI workflows including story generation, subtitle systems, multimodal interaction, and voice-based AI integration.
• Independently handled frontend, backend, AI integration, and system architecture development.