As an ML Developer Intern, I worked diligently to develop a cutting-edge solution for fault detection in semiconductor wafers, gaining valuable experience and deepening my understanding of machine learning in the process.Project Highlights:Automated fault detection using machine learning to analyze sensor data from wafers.Built a custom preprocessing pipeline using scikit-learn, ensuring efficient data handling.Achieved high model accuracy with AUC & F1-scores consistently above 0.95%.Implemented dynamic data drift detection and automated alerts for data quality monitoring.Developed a user-friendly dashboard for both training insights and client predictions.Integrated MLflow for experiment tracking and AWS CloudWatch for real-time log monitoring.Deployed the solution using FastAPI and automated CI/CD with GitHub Actions on AWS.This project enhanced the accuracy and efficiency of wafer inspections, reduced manual work, and minimized production downtime, all while contributing to significant cost savings in semiconductor manufacturing.