AI-powered Resume Search Engine

Modern recruitment processes face significant challenges due to the exponential increase in job applications per vacancy. Conventional Applicant Tracking Systems (ATS) primarily rely on keyword-based filtering mechanisms, which often fail to capture contextual meaning, transferable skills, and semantic relationships within resumes. As a result, qualified candidates may be overlooked, while less suitable applicants may pass screening through strategic keyword optimization.

This paper presents an AI-Powered Semantic Resume Screening System designed to enhance recruitment accuracy, fairness, and authenticity verification. The system integrates Large Language Models (LLMs) for contextual understanding of resumes and job descriptions, enabling semantic similarity-based candidate ranking. It incorporates role-specific skill assessments, plagiarism detection, AI-generated content verification, and automated anonymization of Personally Identifiable Information (PII) to reduce bias.The proposed architecture follows a modular client–server design using Fast API for backend orchestration, Next.js-based frontend interfaces, PyMuPDF and OCR for document processing, and MySQL for structured data storage. Experimental validation demonstrates improved candidate-job alignment, enhanced integrity, and reduced manual recruitment workload. The system represents a next-generation intelligent hiring platform emphasizing transparency, meritocracy, and efficiency.