AI-Powered Resume Skill Matching and Job Recommendation System Using AWS and Generative AI

Abstract

The growing complexity of the modern job market has made it increasingly difficult for candidates to assess their own readiness for specific roles, while recruiters struggle to efficiently screen large volumes of applications. This paper presentsthedesignandimplementationofanAI-poweredresume skillmatchingandjobrecommendationsystemthatbridges this gap by combining cloud-based infrastructure with intelli¬gent natural language processing. The system parses uploaded resumes, extracts technical and domain-specific skills, and com¬pares them against structured job requirement data stored in a cloud database. Using Amazon Web Services (AWS) components including S3, Lambda, and DynamoDB, the platform achieves high scalability and low-latency processing without requiring dedicated server management. Beyond simple matching, the sys¬tem computes a quantitative compatibility score, detects missing competencies, and invokes a Generative AI layer to provide personalised skill improvement recommendations. Evaluation results demonstrate that the system reduces manual screening effort significantly while offering actionable guidance to job seekers.Thisworkcontributesapractical,end-to-endframework that improves both recruitment efficiency and candidate careerdevelopment.

Introduction

The text presents an AI-driven recruitment system designed to solve inefficiencies in traditional resume screening and candidate–job matching. In current hiring processes, recruiters spend excessive time manually reviewing large numbers of resumes, while candidates lack clear feedback on how their skills align with job requirements. Existing systems are often keyword-based, biased, and lack semantic understanding and personalized guidance.

To address these issues, the proposed system uses a cloud-based, serverless architecture (AWS) combined with NLP and Generative AI. It automatically processes uploaded resumes, extracts skills, compares them with job requirements stored in a database, and computes a match score. It also identifies skill gaps and provides personalized learning recommendations through a GenAI module. HR users can post jobs, define required skills, and view ranked candidate lists.

The system pipeline includes resume upload, text extraction, NLP-based skill extraction, skill matching (exact and semantic), match score calculation, gap detection, and AI-generated career guidance. A dashboard presents results for both candidates and recruiters.

Evaluation on 150 resumes shows strong performance, with 91% precision and 87% recall in skill extraction, and good alignment (0.84 correlation) between automated scores and human judgment. Overall, the system improves hiring efficiency, reduces manual workload, and provides transparent, explainable, and personalized recruitment decisions.

Conclusion

This paper presented the design, implementation, and eval¬uation of an AI-powered resume skill matching and job rec¬ommendation system built on AWS serverless infrastructure. The system demonstrates that it is feasible to combine cloud-nativescalabilitywithstate-of-the-artNLPandGenerative AI techniques to deliver a recruitment support platform that benefits both job seekers and employers. The proposed approach addresses the principal limitations of traditional resume screening by replacing subjective, time-consuming manual review with a transparent, data-driven pipeline. Candidates receive objective feedback on their po¬sition relative to job requirements along with personalised guidance on how to improve their competitiveness. HR teams gain a ranked candidate view that supports faster and more consistent shortlisting decisions. Experimental evaluation on a set of 150 test resumes demonstrated a skill extraction precision of 91%, a recall of 87%, and a strong Spearman rank correlation of 0.84 between computed match scores and expert suitability ratings. These results confirm that the system performs well across diverse resume formats and job domains. Future work will focus on integrating the platform with external job portals, introducing resume improvement sug¬gestions, developing an interview preparation module, and expandingmulti-languagesupporttoserveaglobaluserbase.

References

The text presents an AI-driven recruitment system designed to solve inefficiencies in traditional resume screening and candidate–job matching. In current hiring processes, recruiters spend excessive time manually reviewing large numbers of resumes, while candidates lack clear feedback on how their skills align with job requirements. Existing systems are often keyword-based, biased, and lack semantic understanding and personalized guidance. To address these issues, the proposed system uses a cloud-based, serverless architecture (AWS) combined with NLP and Generative AI. It automatically processes uploaded resumes, extracts skills, compares them with job requirements stored in a database, and computes a match score. It also identifies skill gaps and provides personalized learning recommendations through a GenAI module. HR users can post jobs, define required skills, and view ranked candidate lists. The system pipeline includes resume upload, text extraction, NLP-based skill extraction, skill matching (exact and semantic), match score calculation, gap detection, and AI-generated career guidance. A dashboard presents results for both candidates and recruiters. Evaluation on 150 resumes shows strong performance, with 91% precision and 87% recall in skill extraction, and good alignment (0.84 correlation) between automated scores and human judgment. Overall, the system improves hiring efficiency, reduces manual workload, and provides transparent, explainable, and personalized recruitment decisions.

Copyright

Copyright © 2026 Mordeeshvara B, Sushmidha M. This 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.