AI Powered Personalised Mock Interview System

The primary objective of this work is to develop a system that effectively supports candidates in preparing for job interviews, moving beyond static question banks toward an interactive platform capable of responding, evaluating, and explaining performance. The initial implementation demonstrates promising results, indicating that the proposed approach is both feasible and impactful. The Groq AI Engine was selected to enable real-time interview simulation, offering faster response times compared to alternative solutions and thereby enhancing the natural flow of interaction. Firebase proved to be a reliable backend solution for managing data, while ReactJS provided the flexibility required to build a responsive, feature-rich application without unnecessary complexity. Despite these achievements, several areas for improvement remain. The quality of AI-generated feedback for technical questions requires further refinement. Future enhancements include the integration of speech-based responses to create a more realistic interview experience, as well as the incorporation of resume parsing to enable personalized, experience-driven question generation. Additionally, the development of a mobile application is planned, considering the significant number of users accessing the platform via smartphones. The broader implication of this work lies in the ability of AI to provide a level of accessibility and consistency that is difficult to achieve through traditional methods. By offering each user a patient, unbiased, and continuously available interview coach, the system has the potential to significantly improve interview preparedness. With continued development and refinement, AI-driven platforms such as this can play a meaningful role in enhancing candidate performance and confidence in real-world interview scenarios.

[1] S. Sharma, R. Kumar, and A. Singh, "AI-Driven Virtual Mock Interview Development: Enhancing Career Readiness," in Proc. IEEE Int. Conf. on Artificial Intelligence and Smart Systems (ICAIS), Jan. 2024, pp. 215-220. [2] J. M. C. J. M. Sabi et al., "Q&AI: An AI powered mock interview bot for enhancing the performance of aspiring professionals," in Proc. IEEE Int. Conf. Adv. Syst. Eng. (ICASE), Feb. 2024, pp. 1-5. [3] R. Mandal, P. Lohar, D. Patil, and A. Patil, "AI-based mock interview evaluator: An emotion and confidence classifier model," in Proc. 2nd Int. Conf. Emerg. Trends Eng. Manag., Apr. 2023, pp. 1-6. [4] M. E. Hoque et al., "MACH: My Automated Conversation Coach," in Proc. 2013 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp '13), 2013, pp. 697-706. [5] K. Hemamou, G. Felhi, V. Vandenbussche, J. C. Martin, and C. Clavel, "HireNet: Semi-supervised Hierarchical Attention Network for Multimedia Hiring Analysis," in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 3857-3861. [6] I. Naim, M. I. Tanveer, D. Gildea, and M. E. Hoque, "Automated Analysis and Prediction of Job Interview Performance," IEEE Transactions on Affective Computing, vol. 9, no. 2, pp. 191-204, 2018. [7] L. Zhang and M. Chen, "Real-Time NLP Feedback Systems in Educational Simulations," IEEE Transactions on Learning Technologies, vol. 17, no. 2, pp. 442-455, Mar. 2025. [8] T. B. Brown et al., "Language Models are Few-Shot Learners," in Proc. 34th International Conference on Neural Information Processing Systems (NeurIPS), 2020, pp. 1877-1901. [9] S. Goel, G. Saini, and M. Singh, "Automated Evaluation Framework for Programming Assignments," in Proc. 10th IEEE International Conference on Engineering Education, 2021, pp. 45-50. [10] R. Mandal et al., “AI-Based Mock Interview Evaluator: Emotion and Confidence Classifier Model,” in Proc. Int. Conf. Intelligent Systems for Communication, IoT and Security (ICISCoIS), 2023. [11] P. Gupta and S. Mehta, "Optimization of Low-Latency LLM Inference for Interactive Web Applications," Journal of AI Research and Applications, vol. 9, no. 1, pp. 88-102, Jan. 2026.