Professional Overview
I am a Computer Vision Engineer with 2+ years of hands-on experience building production-ready systems for OCR, document AI, object detection, and face recognition, covering the full ML lifecycle from data collection to backend deployment. I have a proven track record of converting slow, manual document processes into automated pipelines—benchmarking tools like Tesseract, DocTR, and Docling, and combining them with custom preprocessing to cut processing time from hours to minutes while improving accuracy on noisy scans.Beyond model development, I design end-to-end architectures using Python, FastAPI, and PostgreSQL, including HLD/LLD, database schemas, and API contracts for real-time, multi-tenant platforms such as camera-based attendance and automated signature verification using YOLOv8, RetinaFace, and ArcFace. Employers should consider me because I do not just build models; I own complete solutions that reduce manual effort, scale reliably in production, and deliver clear, measurable business impact