Degree

Master of Science in Computer Science

Department

Department of Computer Science

School

School of Mathematics and Computer Science (SMCS)

Date of Submission

Fall 2025

Supervisor

Dr. Tariq Mahmood, Professor, School of Mathematics and Computer Science (SMCS)

Committee Member 1

Dr. Muhammad Atif Tahir , Professor and Program Coordinator, Graduate & Postgraduate Programs (CS) School of Mathematics and Computer Science (SMCS) Institute of Business Administration (IBA), Karachi

Keywords

AI Interviews, Speech Recognition, Natural Language Processing, Large Language Models, Microservices Architecture, Real-time Evaluation, Recruitment Technology, Voice-based Interaction

Abstract

The recruitment interview stage remains one of the most resource-intensive and inconsistent parts of modern hiring workflows. Although applicant tracking systems have improved resume screening and scheduling, early-stage interviews still depend heavily on human availability and subjective judgment, limiting scalability and consistency.

This project presents IntelliScreen, an AI-based interview orchestration system designed to support early-stage technical and behavioral interviews through live, voice-based interaction. Rather than attempting to replace human interviewers, the system was deliberately scoped to standardize interview delivery and assessment at scale. IntelliScreen adopts a microservices architecture that combines interview orchestration, speech processing services, an LLM middleware for evaluation and reporting, and a web-based interview portal.

A central design decision in IntelliScreen is the use of real-time response evaluation to guide interview flow. Candidate answers are transcribed, assessed, and used to generate contextual follow-up questions during the interview itself, enabling deeper probing of uncertain responses. The platform was validated through integration with IntelliHire, supporting end-to-end operation from interview initiation to assessment delivery.

Manual testing showed that the system reliably supports real-time voice interaction, produces usable transcriptions, and generates structured assessment reports covering technical and communication performance. These results suggest that a voice-first, modular interview orchestration approach can improve consistency and scalability in early-stage recruitment while remaining compatible with existing hiring platforms.

Document Type

Restricted Access

Submission Type

Research Project

Loading...

Media is loading
 
Download

The full text of this document is only accessible to authorized users.

Share

COinS