Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189269,
        author = {C.B.BhashwithaReddy and Bhashwitha Reddy and Apurva and G Manikanta and K.Poojitha and Mrs Manjubhargavi D.P},
        title = {SCREEINE GEINE USING GEN AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {5928-5932},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189269},
        abstract = {The surge in digital recruitment has triggered a massive influx of resumes for every job vacancy, rendering manual screening methods increasingly impractical, prone to errors, and inefficient. To address these bottlenecks, this research introduces an AI-driven system designed for automated resume screening and Job Description (JD) alignment. By leveraging Large Language Models (LLMs), the proposed solution automates the candidate evaluation life cycle.
The system processes resumes in PDF and DOCX formats, utilizing the Llama-3 8B model via the Groq API to extract and summarize core competencies and professional experience. It performs a sophisticated comparative analysis between the JD and the resume, calculating metrics such as technical keyword density, professional alignment, and a comprehensive suitability index. These metrics allow for a ranked shortlist of candidates, significantly streamlining the recruiter's decision-making process. The entire framework is hosted on a Streamlit interface, providing a seamless user experience for document uploads and data visualization.
Empirical results indicate that the system accurately pinpoints candidate strengths and technical requirements, reducing manual labor without compromising quality. Beyond efficiency, the tool promotes objective hiring by standardizing evaluation parameters. Future iterations will focus on multi-model scoring integration, handling diverse file structures, and evolving the system into a comprehensive, end-to-end Applicant Tracking System (ATS).},
        keywords = {LLM, AI Recruitment Tool ,Automated Resume Evaluation, Candidate Shortlisting, Natural Language Processing, Streamlit, Resume Summarization, Keyword Extraction, Ranking Algorithm},
        month = {December},
        }