International Journal of Scientific Research and Engineering Development

Conventional CV formats often do not adequately represent candidates and their abilities because of their structured formats, inconsistency of design, and issues of compatibility with automated hiring approaches & screens. As ATS (applicant tracking systems) gain popularity, many qualified resumes are filtered out by these systems before they ever reach the review stage of hiring. This work presents a NLP (natural language processing) based framework to address these barriers by providing semantic analysis, skill identification, enhancing keywords, and customizing resumes automatically based on a job description. The framework integrates advanced techniques, such as contextual embeddings, contrastive learning, and skill graph construction, to enhance the accuracy of matching candidates to job openings while providing an equitable and transparent hiring process. Experimental evaluations of the framework demonstrate that using the automated resume screening process improves effectiveness of screening, decreases bias, and allows candidates to obtain feedback to help them align. resume with job openings. This work supports enhanced recruitment processes that promote equitable AI hiring processes.