I am a software engineer dedicated to building intelligent creative tools that empower users through technology. My work bridges the gap between complex AI/Computer Vision research and high-performance, browser-based cinematic experiences. I specialize in the TypeScript and Python ecosystems, focusing on scalable architectures that deliver seamless user experiences.
- 🔭 Currently working on: Advancing AI-driven video analysis and browser-based cinematic studios.
- 🌱 Learning: Deep dive into LLM orchestration and real-time media processing pipelines.
- 👯 Looking to collaborate on: Open-source AI tools and innovative frontend animation libraries.
- 💬 Ask me about: Computer Vision in the browser, React performance, or building monetization-safe AI apps.
| Project | Description | Tech Stack |
|---|---|---|
| VibeMatch AI | Intelligent music matchmaker analyzing video mood, tempo, and semantics with CLIP to find monetization-safe CC0 tracks. | Python Streamlit CLIP OpenCV |
| StopFrame | Browser-based studio instantly converting standard video into professional stop-motion animation using client-side HTML5 Canvas. | React Vite Framer Motion Canvas |
| CVD Vision AI | AI accessibility platform with personalized calibration, semantic color remapping, and WCAG auditing for Color Vision Deficiency. | React FastAPI TensorFlow.js OpenCV |
| Statistics Toolkit | Professional predictive analytics suite featuring automated assumption audits and an Ollama-powered local hybrid RAG engine. | Python Flask Ollama Scikit-Learn |
| AI Text Summarizer | Advanced NLP web application for real-time article summarization with adjustable length and ROUGE performance metrics. | Python Streamlit Hugging Face PyTorch |