AI Interview Simulator: An Intelligent Hiring & Preparation Assistant

DOI

10.2991/978-94-6463-858-5_107How to use a DOI?

Keywords

Large Language Models (LLMs); Whisper; LoRA; Natural Language Processing (NLP)

Abstract

The current recruitment process suffers from inconsistent interview experiences, uneven candidate evaluation, and a time-consuming process of administration of manual assessments. To resolve these problems, we develop an AI based Interview Simulator that normalizes the interview procedure, making it more comfortable, parallel, objective and scalable. Since our system takes advantage of advanced AI technologies such as speech recognition, as well as a fine-tuned Llama language model, our system offers a smooth, real-time interview to better evaluate candidates. Our solution provides Whisper OpenAI Speech-to-Text for speech to text recognition, and a custom fine-tuned Llama model on top of LoRA for intelligent and context aware messages. The system built on top of a web application based on Flask supports adaptive questioning in real time, conversation recording, as well as session tracking to track every step of the candidate assessment process thoroughly. It is trained using a curated set of interview questions and answers so that the AI model can be optimized for its domain of interactions specifically. We perform a performance analysis of our system, and show that speech transcription is very accurate, contextually and naturally responsive AI responses, and interview preparation time is cut down by approximately 60 percent. As research on transforming AI into modern recruitment, it shows how AI could provide a more efficient, unbiased, and technology-based approach to recruit talent.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Gugulothu Venkanna
AU  - Dikkala Mohana Yogesh
AU  - Jupally Yashwanth Rao
AU  - Kantubhukta Sai Preetham
PY  - 2025
DA  - 2025/11/04
TI  - AI Interview Simulator: An Intelligent Hiring & Preparation Assistant
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 1283
EP  - 1292
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_107
DO  - 10.2991/978-94-6463-858-5_107
ID  - Venkanna2025
ER  -