AI-Based Career Copilot for Skill Gap Analysis and Job Recommendation Using Semantic Embeddings

The Intelligent Career Guidance using AI-Powered Career Copilot provides an efficient way to provide intelligent ca-reer guidance using state-of-the-art natural language process-ing methods. It uses SBERT-based semantic embedding and FAISS indexing to achieve efficient and accurate job matching. The system is efficiently able to parse resume, extract skills, analyze skill gap, generate quizzes, and evaluate resumes. Moreover, with the help of live job APIs, the system can deliver the most recent jobs, and the personalized learning path can help users develop their skillsets. The experiment results show that the system is highly accurate and relevant. The use of the semantic similarity method increases the accuracy of job matching. Overall, the system is scalable and efficient, which makes it very useful for students and job seekers.

[1]     V. Ramazanova, G. Alibekova, S. Adilova, and G. Turdalykyzy, “De-velopment of a Knowledge Graph-Based Model for Recommending MOOCs to Supplement University Educational Programs in Line With Employer Requirements,” IEEE Access, vol. 12, pp. 128945–128960, 2024. [2]     P. C. Siswipraptini, A. P. Putra, A. S. Subekti, and S. W. Purnama, “Personalized Career Path Recommendation Model for IT Students in Indonesia,” IEEE Access, vol. 12, pp. 115732–115744, 2024. [3]     M. Shoaib, S. Bhatia, A. Gupta, and R. M. Rahman, “Automated Generation of MCQs for Computer Science Education Using cGANs,” IEEE Access, vol. 13, pp. 21025–21038, 2025. [4]     A. K. Sharma, R. Deshmukh, N. Patel, and S. Iqbal, “A Flask–PHP Based Job Recommendation System Using Cosine Similarity and TF–IDF,” International Journal of Advanced Research in Science, Com-munication and Technology (IJARSCT), vol. 4, no. 2, pp. 88–95, 2024. [5]     S. Haryan, A. Jain, R. Sharma, and K. Kapoor, “FairHire: A Fair and Automated Candidate Screening System,” in Proc. Int. Conf. Computa-tional Intelligence and Data Science, pp. 312–325, 2024. [6]     E. Salakar, N. Aljuaid, M. Hossain, and J. Alghamdi, “Resume Screening Using Large Language Models,” in Proc. IEEE Int. Conf. Advances in Science and Technology (ICAST), pp. 225–230, 2023. [7]     N. Rashi and V. Mohan, “Automatic Resume Screening Using SBERT,” International Journal for Multidisciplinary Research (IJFMR), 2025. [8]     D. Lavi, V. Medentsiy, and D. Graus, “conSultantBERT: Fine-tuned Siamese Sentence-BERT for Matching Jobs and Job Seekers,” arXiv preprint arXiv:2109.06501, 2021. [9]     D. Kanikar, P. Jain, S. Jain, and L. Purohit, “Systematic Review of Methods for Analysis of Resumes,” Advances in Computer Science Research, 2025. [10]    B. Kinge, S. Mandhare, P. Chavan, and S. M. Chaware, “Resume Screening using Machine Learning and NLP: A Proposed System,” International Journal of Scientific Research in Computer Science, En-gineering and Information Technology (IJSRCSEIT), vol. 8, no. 2, pp. 253–258, 2022.