I build AI systems that move from research experiments into usable products: computer vision services, medical image analysis pipelines, OCR and ASR workflows, LLM-RAG systems, multimodal auto-labeling platforms, and optimized model APIs. My work spans images, video, text, tabular data, and biosignals, with a strong emphasis on clean data pipelines, reproducible evaluation, and deployment-aware model design.

The core of my profile is applied AI engineering: PyTorch-based deep learning, YOLO and MediaPipe vision systems, FastAPI/Docker deployment, model optimization, and multimodal AI workflows. My research interests sit around medical AI, neuroimaging, biomedical signal processing, and brain-computer interfaces, especially where rigorous machine learning can support more interpretable and reliable systems.