I’m a mechanical engineer by training, software engineer by practice, and now working as an AI/ML engineer focused on building real-world applications that bridge data, intelligence, and automation.
Over the past few years, I’ve transitioned from designing physical systems to developing software, and now to applying deep learning across computer vision and document AI tasks, always with an emphasis on deployable, user-focused tools.
Currently focused on:
- Computer Vision, Deep Learning, and Real-Time Inference
- Agentic AI systems, RAG pipelines, and document intelligence chatbots
- Startup ideation and applied machine learning for space, productivity, and beyond
Latest Project
ScanlyAI — Intelligent Document Processing
A document AI tool that extracts data from receipts and invoices, providing clean summaries and insights. Built with FastAPI, GPT-5, and React.
ClayBot — AI-Powered Personal Website Assistant
An AI assistant embedded in my portfolio, trained on my project docs to answer questions using GPT-3.5 and Supabase pgvector.
Face Mask Detection with YOLOv5l
Built a multi-class face mask detection system using YOLOv5l, fine-tuned on the Kaggle Face Mask Detection dataset.
- PyTorch + TensorFlow for vision and sequence models
- Neural networks (CNNs, LSTMs, Transformers)
- Cloud deployment (Hugging Face, GCP, AWS)
- Python, FastAPI, and ReactJS
Let’s connect: LinkedIn →
Open to freelance, research, and startup collaborations!
