Automated ML pipeline for Iris dataset classification using Decision Tree. Features PCA dimensionality reduction and standard scaling.

End-to-end MLOps pipeline showcasing senior-level best practices with Hydra for configuration, MLflow for experiment tracking, Optuna for hyperparameter tuning, and DVC for data/version control. This repository focuses on reproducibility, modular design, and streamlined collaboration—an ideal demonstration of advanced MLOps capabilities.

An end-to-end machine learning web app that classifies PDF resumes into job-fit categories. Built with FastAPI, Streamlit & Docker. Deployed on Render.

The "Insurance Claims MLOps Lifecycle Automated Pipeline" GitHub project offers an efficient solution for insurance claim processing. Leveraging Azure services, it covers data engineering, model development, MLOps integration, deployment, and application. Automated pipelines streamline workflows, ensuring robust, scalable production environments.