Intelligent Resume Generation Using Generative AI and Full-Stack Web Technologies
International Journal of Advanced Research in Science Communication and Technology · 14.05.2026 · 538
DOI: 10.48175/ijarsct-35371 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advanced Research in Science Communication and Technology, online erschienen am 14.05.2026. Verfasst von Anmoldeep Chauhan und 2 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben.
Abstract (Originalsprache)
The rapid growth of digital recruitment has made the quality and structure of a resume more decisive than ever in determining a candidate's ability to pass automated screening. Applicant Tracking Systems (ATS) now serve as the primary filter in the hiring pipeline of most medium and large organizations, and research consistently shows that over three-quarters of submitted resumes are eliminated before a human recruiter reads them — not due to candidate unsuitability, but due to structural and keyword-related resume deficiencies. Despite this, the majority of free resume-building tools available today offer no meaningful AI-powered content assistance, no ATS optimization, and no integrated live preview. This paper describes the design, development, and evaluation of a full-stack AI-powered Resume Builder web application that addresses these gaps comprehensively. The system enables users to input professional details across structured sections — personal information, educational background, technical skills, work experience, projects, and a professional summary — and generates a polished, ATS-optimized resume document in real time. The platform integrates the Google Gemini large language model API on the server side to perform context-aware content enhancement, improving professional tone, grammar, action verb usage, and keyword density without exposing the API key to the client. The frontend is constructed using React.js with the Context API for centralized state management and Tailwind CSS for responsive styling, while the backend is implemented on Node.js with Express.js, connected to a normalized MySQL relational schema of eight tables. Security is enforced through JSON Web Token authentication, bcrypt password hashing with a cost factor of 10, parameterized SQL queries for injection prevention, and environment variable-based secret management. System evaluation across all major functional areas confirms correct operation of all API endpoints, enforcement of all validation rules, and resistance to standard security attack vectors including SQL injection and unauthorized cross-user data access. The platform outperforms all reviewed free alternatives across a comprehensive feature matrix. Future work encompasses job-description keyword matching, LinkedIn data import, and a cross-platform mobile client
Zitieren
APA
Chauhan, A., Lata, M., & Singh, R. (2026). Intelligent Resume Generation Using Generative AI and Full-Stack Web Technologies. International Journal of Advanced Research in Science Communication and Technology, 538. https://doi.org/10.48175/ijarsct-35371
Vancouver
Chauhan A, Lata M, Singh R. Intelligent Resume Generation Using Generative AI and Full-Stack Web Technologies. International Journal of Advanced Research in Science Communication and Technology. 2026:538. doi:10.48175/ijarsct-35371
BibTeX
@article{Chauhan2026,
author = {Chauhan, Anmoldeep and Lata, Manju and Singh, Rajendra},
title = {Intelligent Resume Generation Using Generative AI and Full-Stack Web Technologies},
journal = {International Journal of Advanced Research in Science Communication and Technology},
year = {2026},
pages = {538},
doi = {10.48175/ijarsct-35371}
}
EUVIMED