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{208573,
        author = {Mohd Amaan Iqbal Chowlkar and Zobiya Aejaz Rakhangi and Shaikh Faiza Mohd Akbar and Mohammad Zaid Mohammad Wassim Golandaz and Noorusabah Sayed},
        title = {CareerNova: A Proposed Integrated AI-Powered Framework for Resume Generation, ATS Analysis, Personalized Interview Coaching, And Job Recommendation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {520-539},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=208573},
        abstract = {The transition from academic education to professional employment requires candidates to address multiple interconnected tasks, including resume creation, Applicant Tracking System (ATS)-oriented optimization, interview preparation, and identification of suitable job opportunities. Existing career-support tools generally address these tasks independently, requiring candidates to use multiple platforms and repeatedly provide the same information. This paper presents CareerNova, a proposed integrated artificial-intelligence-based career assistance system that combines four modules: an automated resume maker, ATS-oriented resume evaluation and improvement, personalized interview coaching, and job recommendation. The proposed system maintains a structured candidate profile that is reused across the modules to enable consistent personalization. The resume module employs structured information extraction, large language models, and template-based document generation to create professionally organized resumes from candidate-provided information. The ATS module combines deterministic resume analysis, keyword and structural matching, and semantic similarity using sentence embeddings to evaluate resume–job-description alignment and generate actionable improvement recommendations. The interview module uses resume and job-description information to generate personalized questions and supports text- and speech-based mock interviews, with responses evaluated using speech recognition, natural language processing, and AI-assisted semantic analysis. The job recommendation module combines semantic embeddings with structural matching of skills, education, experience, and keywords to generate job-fit scores and interpretable skill-gap information. The proposed framework demonstrates how deterministic analysis and generative AI can be integrated within a unified career-support pipeline. The proposed architecture is designed to provide candidate-specific resume guidance, ATS-oriented compatibility analysis, interview preparation, and explainable job recommendations. The framework provides a foundation for future prototype development and empirical evaluation involving larger-scale user studies and performance validation.},
        keywords = {.},
        month = {September},
        }