SWIPEHIRE: A DUAL-MODE AI-DRIVEN JOB MATCHING PLATFORM FOR CANDIDATES AND RECRUITERS

Abstract

The rapid growth of the digital job market has made traditional hiring platforms increasingly inefficient, with candidates spending excessive time browsing irrelevant listings and recruiters manually screening large volumes of unsuitable applications. In this work, we present SwipeHire, a dual-mode AI-supported hiring platform that reimagines job discovery and recruitment through a swipe-based interaction model inspired by modern consumer applications, combined with a transparent, rule-based skill-matching algorithm. The system supports two distinct user roles — candidates and recruiters — each guided through a tailored onboarding and profile-setup flow. Candidates browse job postings as swipeable cards annotated with an AI-generated match percentage derived from skill-overlap scoring, while recruiters review AI-ranked candidate profiles based on a composite fit score incorporating skill alignment, resume completeness, and relevant experience. A mutual right-swipe from both parties triggers an automatic match, unlocking a real-time chat channel built on WebSocket technology that supports text messaging, file sharing, and recruiter-initiated interview requests. The platform further provides candidates with a growth analytics dashboard visualizing application trends and in-demand skills, and recruiters with a recruiting analytics dashboard tracking shortlist rates and job performance. Administrative controls for user management and company verification, together with JWT-based authentication, password hashing, and rate-limiting, ensure the platform is both usable and secure. Implemented using the MERN stack (MongoDB, Express.js, React.js, Node.js) with Socket.IO for real-time communication, SwipeHire demonstrates that an explainable, algorithm-driven matching approach can deliver a fast, engaging, and trustworthy hiring experience for both job seekers and employers.