The thesis focuses on bridging the gap between job seekers and recruiters through an automated job application platform that uses advanced data collection and machine learning techniques. The project outlines the current issues in the job market, including communication barriers and skill mismatches that result in inefficiencies for both job seekers and recruiters. It proposes a solution involving a platform that automates CV analysis, job matching, and skill extraction using technologies like Python, Selenium for web scraping, and machine learning models such as BERT and SpaCy for skill recognition. The backend is built with Flask, and the system integrates Apache Airflow for task automation and Power BI for data visualization. The project demonstrates effective handling of data extraction, processing, and enrichment, which enables real-time job market insights. Future enhancements include expanding data sources, advanced analytics, and developing a mobile version for broader accessibility.