AI Powered Mock Interview System

This research introduces a system that uses artificial intelligence to help people get ready for job interviews. The system combines two technologies: one that reads and understands text on resumes and another that analyzes how people behave on video. It helps figure out if someone's ready for a job. The system uses a tool that helps companies track job applicants so people can make their profiles better for job searches. It also has a feature that stops people from cheating during tests. The results show that the system can spot signs of how people behave, like where they look and how they feel. This gives people feedback that they do not get from regular practice interviews. The goal of AceTheJob is to provide high-quality interview coaching to everyone. This can help reduce stress and improve people's chances of getting a job. The system provides an evaluation of a candidate's readiness for a job interview. It uses Artificial Intelligence to bridge the gap between learning and getting hired. AceTheJob helps candidates prepare for job interviews. Provides feedback to improve their performance.  

[1]              A. Vaswani et al., “Attention Is All You Need,” 2023. [2]            S. Minaee et al., “Large Language Models: A Survey,” Mar. 2025, [Online]. Available: http://arxiv.org/abs/2402.06196 [3]            V. B. Parthasarathy, A. Zafar, A. Khan, and A. Shahid, “The ultimate guide to fine-tuning LLms from basics to breakthroughs: An exhaustive review of technologies, research, best practices, applied research challenges and opportunities,” Oct.2024, [Online]. Available: http://arxiv.org/abs/2408.13296 [4]            J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” May 2019, [Online]. Available: http://arxiv.org/abs/1810.04805 [5]            J. Kaplan et al., “Scaling Laws for Neural Language Models,” Jan. 2020, [Online]. Available: http://arxiv.org/abs/2001.08361 [6]            L. Ouyang et al., “Training language models to follow instructions with human feedback,” Mar. 2022, [Online]. Available: http://arxiv.org/abs/2203.02155 [7]            A. Radford, J. Wu, R. Child, D. Luan, D. Amodei, and I. Sutskever, “Language Models are Unsupervised Multitask Learners.” [Online]. Available: https://github.com/codelucas/newspaper [8]            H. Touvron et al., “LLaMA: Open and Efficient Foundation Language Models,” Feb. 2023, [Online]. Available: http://arxiv.org/abs/2302.13971 [9]            T. B. Brown et al., “Language Models are Few-Shot Learners,” Jul. 2020, [Online]. Available: http://arxiv.org/abs/2005.14165 [10]         C. Raffel et al., “Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer,” Sep. 2023, [Online]. Available: http://arxiv.org/abs/1910.10683