Full Text PDF
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Impact Factor (2025): 6.9
DOI Prefix: 10.47001/IRJIET
Vol 10 No 5 (2026): Volume 10, Issue 5, May 2026 | Pages: 537-547
International Research Journal of Innovations in Engineering and Technology
OPEN ACCESS | Research Article | Published Date: 26-05-2026
Today hiring teams often have to wade through hundreds sometimes thousands of resumes for one job opening. Reviewing all of them manually takes a lot of time, can be inconsistent and may be subject to unconscious bias. Traditional applicant tracking systems attempt to make this easier, but most of them rely heavily on keyword matching. This creates a problem - a strong candidate could be missed simply for using different language, while someone with plenty of keywords on their resume could be unfairly favoured. These limitations underscore the need for a smarter, more context-aware approach to resume screening.
This paper introduces HireSyncAI, a unified, cloud-based hiring platform that consolidates multiple technologies into a single system. It leverages Groq-hosted Large Language Models (Llama 3.3-70B) for resume analysis, a Supabase PostgreSQL backend for real-time data processing, SendGrid for automated email communication, and a React TypeScript frontend for HR managers and candidates. "Instead of just looking for keywords, the system reads the resumes more in a human-like way, assessing what a candidate actually knows and has done, and how well that matches the job requirements. Each candidate undergoes a structured assessment that provides a weighted relevance score based on skills (50%), experience (30%), and education (20%), ensuring clear and easily justifiable results.
We tested our system on 50 resumes and each resume was used for five different job roles. The results looked promising. HireSyncAI agreed strongly with human judgment, with a Spearman rank correlation of 0.85. It took under 5 seconds to process each resume, about 1.2 seconds to sync data between sessions, and 98% of emails were successfully delivered. Apart from these metrics, the platform also significantly reduces manual work on the part of recruiters, and makes the hiring process more consistent, transparent, and fair.
Al Hiring, Resume Ranking, Natural Language Processing, Large Language Models, Groq API, Recruitment Automation, Semantic Matching, Supabase, React TypeScript, Applicant Tracking System.
Vanga Sanjana, Vinjam Vineela, Manas Kumar Rath, & Paramesh. (2026). HireSyncAI: An AI-Driven Hiring and Resume Ranking Agent Using Large Language Models and Cloud-Synchronized Multi-Role Architecture. International Research Journal of Innovations in Engineering and Technology - IRJIET, 10(5), 537-547. Article DOI https://doi.org/10.47001/IRJIET/2026.105074
This work is licensed under Creative common Attribution Non Commercial 4.0 Internation Licence
A.Sabarirajan et al., "Intelligent AI-Based Resume Screening and Ranking Framework for Unbiased and Scalable Recruitment Automation," International Journal of Intelligent Systems, vol. 40, no. 1, pp. 1-15, 2025.
A.L. Hunkenschroer and C. Luetge, "Ethics of AI Enabled Recruiting and Selection: A Review and Research Agenda," Journal of Business Ethics, vol. 178, no. 4, pp. 977-1003, 2022.
Arokiaraj S., Amudha T., and S. Ramakrishnan, "Applicant Resume Tracking System (ARTS): GenAI Agent," International Journal of Advanced Computer Science and Applications, vol. 15, no. 3, pp. 1-10, 2024.
R. Mehta, S. Jain, and P. Kulkarni, "Automated Resume Screening Using Machine Learning Techniques," International Journal of Computer Applications, vol. 183, no. 25, pp. 10-15, 2021.
K. Sharma, A. Verma, and R. Singh, "Resume Ranking System Using Natural Language Processing," International Journal of Engineering Research & Technology (IJERT), vol. 11, no. 6, pp. 850-856, 2022.
F. Zheng, C. Zhao, M. Usman, and P. Poulova, "From Bias to Brilliance: The Impact of Artificial Intelligence Usage on Recruitment Biases in China," IEEE Transactions on Engineering Management, vol. 71, pp. 14155- 14170, 2024.
N. Alsubaie and N. Aleisa, "Mitigating Bias in AI Model Using Explainable AI in Terms of Hiring Process in the Industry," IEEE Access, vol. 13, pp. 147218-147230, 2025.
P. Sinha, S. Patro, and A. K. Padhi, "Automated Resume Categorization Using TF-IDF and SVM," International Journal of Computer Applications, vol. 180, no. 12, pp. 34-39, 2018.
S. Maheshwary, H. Misra, and R. Saini, "Automated Job Resume Matching Using Deep Learning," in Proc. IEEE International Conference on Data Mining Workshops (ICDMW), 2018, pp. 1105-1112.
C. Qin, H. Zhu, T. Xu, C. Zhu, L. Jiang, E. Chen, and H. Xiong, "Enhancing Person-Job Fit for Talent Recruitment: An Ability-Aware Neural Network Approach," in Proc. ACM SIGIR, 2018, pp. 25-34.
K. Kenthapadi, B. Le, and G. Venkataraman, "Personalized Job Recommendation System at LinkedIn," in Proc. ACM RecSys, 2017, pp. 360-361.
Y. Luo, H. Zhang, W. Xu, and H. Wu, "PJFNN: Partner Job Fitting Neural Network for PersonJob Fit," in Proc. ACM SIGIR, 2019, pp. 205- 214.
Y. Zheng, J. Zhang, Y. Ma, and C. Qin, "Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval," in Proc. ACL, 2021, pp. 1961-1970.
B. Le, R. White, and R. Baeza-Yates, "Fairness in Automated Resume Screening: A Survey of Bias Sources and Mitigation Approaches," ACM Computing Surveys, vol. 54, no. 7, pp. 1-35, 2022.
P. Tambe, P. Cappelli, and V. Yakubovich, "Artificial Intelligence in Human Resources Management: Challenges and a Path Forward," California Management Review, vol. 61, no. 4, pp. 15-42, 2019.
D. F. Mujtaba and N. R. Mahapatra, "Ethical Considerations in AI-Based Recruitment," in Proc. IEEE International Symposium on Technology and Society (ISTAS), 2019, pp. 1-7.
J. Gonzalez, H. Wang, and M. Singh, "Resume Parsing and Candidate Ranking: An NLP and Rule-Based Approach," Journal of Information Science and Engineering, vol. 37, no. 3, pp. 617-631, 2021.
J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, "BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding," in Proc. NAACL-HLT, 2019, pp. 4171-4186.
T. Brown, B. Mann, N. Ryder et al., "Language Models are Few-Shot Learners," Advances in Neural Information Processing Systems (NeurIPS), vol. 33, pp. 1877-1901, 2020.
H. Touvron, L. Martin, K. Stone et al., "Llama 2: Open Foundation and Fine-Tuned Chat Models," arXiv preprint arXiv:2307.09288, 2023.
A.Vaswani, N. Shazeer, N. Parmar et al., "Attention Is All You Need," Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
X. Chen, Y. Liu, and R. Zhang, "Semantic Matching for Job Recommendation: A Deeр Learning Approach," Expert Systems with Applications, vol. 168, Art. no. 114394, 2021.