This project focuses on building an AI-powered system to automatically categorize resumes into relevant job roles, helping streamline the recruitment and shortlisting process. The goal was to reduce manual resume screening by applying machine learning and NLP techniques to classify resumes accurately based on their content. The system takes resume PDFs as input, extracts and preprocesses the text using PyPDF, and applies Natural Language Processing (NLP) techniques such as text cleaning, tokenization, and TF-IDF vectorization to convert unstructured resume text into numerical features. These features are then fed into a machine learning classification model (scikit-learn) trained to predict suitable job categories like Python Developer, Data Scientist, Web Developer, etc.To make the solution practical and user-friendly, I built an interactive web application using Streamlit, where HR users can upload single or multiple resumes, instantly view predicted job roles, and download the categorized results as a CSV file. The trained model and vectorizer were serialized using Pickle, ensuring fast inference without retraining. This project demonstrates my ability to work end-to-end on an ML system—covering data preprocessing, feature engineering, model training, evaluation, and deployment—while also focusing on usability and real-world HR use cases. Tech Stack: Python, Streamlit, scikit-learn, TF-IDF, NLP, PyPDF, Pandas, Pickle, Git/GitHub