Enhancing Recruitment Efficiency Through AI-Driven Resume Screening and Skill Assessment

A typical recruitment process in an organization is considered a time-consuming process since many manual steps are involved. Besides this, there also exist biases leading them toward inefficiencies, causing bad candidate-job matches. The present paper articulates the design of Revit-an AI recruitment platform pursuing automation in candidate evaluation and enhancement thereof by NLP and ML techniques. Revit provides a two-step evaluation framework: resume screening using semantic similarity analysis and an auto-generated domain-specific quiz for testing technical skills. The system uses some functionality from spaCy and sentence-transformers, as well as Firebase infrastructure, in order to formalize hiring workflows, minimize human-in-loop decisions, and aid in making data-driven decisions. An empirical evaluation on a data set containing 500 resumes and 50 job postings showed that the system could match candidates against jobs with a 95% accuracy and reduce screening time by 70%. Thus, proving that AI can enhance recruitment processes to achieve scalability, fairness, and transparency.