Home / Current Issue / Paper 1712907
Aurora AI ? An AI-Powered Career Optimization Tool
Subject area: Science,Engineering and Technology · Area of research: AIML
Abstract
An AI-powered career optimization tool called Aurora AI gives job seekers real-time, useful insights into their LinkedIn profiles and resumes while putting privacy first.In order to ensure that personal data never leaves the user's device, it was designed as a browser-based Single Page Application (SPA) with 100% client-side processing. The system uses the Google Gemini API to offer quantitative scoring (Resume Fit Score, ATS Compatibility, Profile Completeness), customised improvement recommendations that align with specific job descriptions, and keyword gap analysis. A context-aware AI chat assistant enables interactive, follow-up guidance based on the most recent analysis results. Through serverless architecture and secure API key handling, Aurora AI prioritises security while offering a visually appealing Aurora-themed user interface, accessibility compliance, and responsive design. The only resume formats supported at the moment are PDFs and manual LinkedIn input. Keywords: Prompt Engineering, Gemini API, Ameena AI, Intelligent Tutoring Systems, Personalised Learning, Multimodal Learning, Self-Regulated Learning, Artificial Intelligence in Education, and React SPA. In the future, browser extensions, user accounts, and compatibility with.docx will be added. Aurora AI fills the gap between individualised, privacy-preserving career counselling and generic applicant tracking systems.
Keywords
Career Optimisation Driven by AI, Privacy-Preserving Resume Analysis, Client-Side Processing, Compatibility with Applicant Tracking Systems (ATS), and Context-Aware Conversational Assistant
References
[1] Bhatia, A., Gupta, S., & Verma, A. (2019). End-to-End Resume Parsing and Finding Candidates using BERT. arXiv preprint arXiv:1908.03868.
[2] Zhang, J., Ma, K.-L., & Elmqvist, N. (2017). Visual Analytics for Semantic Resume Data: ResumeVis. ArXiv preprint arXiv:1709.08146.
[3] Patil, S., Zinjad, P., and Kumar, R. (2024). ResumeFlow: Customised Resume Creation Assisted by LLM. ArXiv preprint arXiv:2402.01234.
[4] Lee, H., Lai, P., & Wong, C. (2016). CareerMapper : LinkedIn evaluation done automatically. ArXiv preprint arXiv:1605.04523
[5] Patel, M., Sharma, P., and Daryani, S. (2020). intelligent system for matching resumes. 8(5), 32–38; International Journal for Research in Applied Science & Engineering Technology (IJRASET).
[6] Improved candidate matching by the use of semantic analysis. Advances in Science, Technology & Engineering Systems Journal, 6(3), 456–465, ASTESJ, 2021.
[7] Giri, S., and Anand, R. (2023). ATS Resume Design Optimisation with LLM. ResearchGate
[8] MDPI Electronics (2023). Intelligent Resume Embeddings: Resume2Vec. Electronics MDPI, 12(5), 987-1005.
[9] Vanetik, O., and Vanetik, N. (2022). Parsing resumes and ranking vacancies with embeddings. Information, MDPI, 13(8), 393*.
[10] Thomas, V., George, P., and Omanakuttan, S. (2024). Intelligent system for resume tracking.
[11] Das, T., Rahman, F., and Ahmed, R. (2024). AI- Recommended Intelligent Resume Screening Tool. ResearchGate.
[12] Contributors to Wikipedia. (2022). Return to Semantic Search and Parsing. The Free Encyclopaedia, Wikipedia. taken fromthe followingpage: https://en.wikipedia.org/wiki/Resume_parsing
[13] Contributors to Wikipedia. (2025). AI in the hiring process. The Free Encyclopaedia, Wikipedia. This information was taken from https://en.wikipedia.org/wiki/Artificial_intelligence_in_hiring.
[14] Guide to ReZoom.io, 2023. Optimising resume keywords for applicant tracking systems. retrieved from https://www.rezoom.io/ats-resume-keywords.
[15] Patil, A., Bhor, P., & More, S. (2023). Smart Resume Analyser (extraction of RNN keywords). ResearchGate
How to cite this paper
@article{1712907,
author = {Dr. M Rajasekaran, Sayed Abdul Biya Bani, Tallapaneni Lakshmi Srivardhan, Penigi Siva Nagendra Rama Lakshmi Deepak, Vavilli Audi Shankar},
title = {Aurora AI ? An AI-Powered Career Optimization Tool},
journal = {Iconic Research And Engineering Journals},
year = {2025},
volume = {9},
number = {6},
pages = {1241-1248},
issn = {2456-8880},
url = {https://www.irejournals.com/formatedpaper/1712907.pdf},
abstract = {An AI-powered career optimization tool called Aurora AI gives job seekers real-time, useful insights into their LinkedIn profiles and resumes while putting privacy first.In order to ensure that personal data never leaves the user's device, it was designed as a browser-based Single Page Application (SPA) with 100% client-side processing. The system uses the Google Gemini API to offer quantitative scoring (Resume Fit Score, ATS Compatibility, Profile Completeness), customised improvement recommendations that align with specific job descriptions, and keyword gap analysis. A context-aware AI chat assistant enables interactive, follow-up guidance based on the most recent analysis results. Through serverless architecture and secure API key handling, Aurora AI prioritises security while offering a visually appealing Aurora-themed user interface, accessibility compliance, and responsive design. The only resume formats supported at the moment are PDFs and manual LinkedIn input. Keywords: Prompt Engineering, Gemini API, Ameena AI, Intelligent Tutoring Systems, Personalised Learning, Multimodal Learning, Self-Regulated Learning, Artificial Intelligence in Education, and React SPA. In the future, browser extensions, user accounts, and compatibility with.docx will be added. Aurora AI fills the gap between individualised, privacy-preserving career counselling and generic applicant tracking systems.},
keywords = {Career Optimisation Driven by AI, Privacy-Preserving Resume Analysis, Client-Side Processing, Compatibility with Applicant Tracking Systems (ATS), and Context-Aware Conversational Assistant},
month = {December},
doi = {https://doi.org/10.64388/IREV9I6-1712907}
}