Thirupat Thirupat

I am a machine learning engineer with hands-on experience building end-to-end AI systems for NLP and computer vision applications. I develop pipelines for data ingestion, model training, hyperparameter tuning, and production inference.

My projects include a sentiment and customer-segmentation pipeline processing 10k+ feedback entries, a real-time CV system for crowd analytics using YOLOv8, and a multi-modal RAG assistant integrating LangChain, Chroma DB, and large models. I focus on measurable improvements — for example, improving a Random Forest from 84% to 87% accuracy through tuning.

I have deployed services with Flask and Streamlit and implemented transcription, translation, and TTS workflows for real-time Q&A. My internship work involved analyzing business datasets and building regression and classification models to deliver actionable insights.

I hold a Computer Science degree and several certificates in data analysis, deep learning, and full-stack data science, and I actively solve competitive programming problems to keep my coding skills sharp.