I build production-ready ML systems that bridge deep learning research and reliable products.
With dual Master’s degrees in AI & Visual Computing, I specialize in Computer Vision, MLOps and LLM-powered applications.
🔬 Core domains
- Computer Vision: detection, segmentation, tracking, OCR, medical imaging
- LLMs & Retrieval (RAG, LangChain, multimodal models)
- Scalable ML systems: containerized services, FastAPI, MLflow, GitHub Actions, CI/CD
🎯 Mission: Build robust, explainable, and impactful AI that bridges research and industry.
🔹 Smart Vehicle Detector
Real-time detection and characterization of vehicles (type, color, manufacturer, country) using YOLOv12 + Vision-Language Models.
YOLOv12 · VLM · Multimodal AI · Docker · JSON Output API
🔹 HealthRAG
Medical chatbot powered by Retrieval-Augmented Generation with LangChain, Hugging Face and FAISS.
RAG · LLMs · LangChain · Hugging Face · Flask
🔹 CapsNet for Medical Imaging
3D CT-scan classification using Capsule Networks and Gabor filters.
CapsNet · TensorFlow · Data Augmentation · Medical AI
“AI isn’t just about intelligence — it’s about creating systems that serve and empower people.”