AI-Driven Decision-Making System for Hiring Process

TL;DR

This paper introduces an AI-driven modular hiring assistant that streamlines candidate validation by integrating multiple data sources, scoring, and human oversight, significantly reducing screening time and costs.

Contribution

It presents a novel multi-agent system orchestrated by an LLM for efficient, transparent, and human-in-the-loop candidate evaluation in hiring processes.

Findings

Reduces screening time from 3.33 to 1.70 hours per qualified candidate.

Improves throughput and lowers screening costs.

Maintains human final decision authority.

Abstract

Early-stage candidate validation is a major bottleneck in hiring, because recruiters must reconcile heterogeneous inputs (resumes, screening answers, code assignments, and limited public evidence). This paper presents an AI-driven, modular multi-agent hiring assistant that integrates (i) document and video preprocessing, (ii) structured candidate profile construction, (iii) public-data verification, (iv) technical/culture-fit scoring with explicit risk penalties, and (v) human-in-the-loop validation via an interactive interface. The pipeline is orchestrated by an LLM under strict constraints to reduce output variability and to generate traceable component-level rationales. Candidate ranking is computed by a configurable aggregation of technical fit, culture fit, and normalized risk penalties. The system is evaluated on 64 real applicants for a mid-level Python backend engineer role, using an experienced recruiter as the reference baseline and a second, less experienced recruiter for additional comparison. Alongside precision/recall, we propose an efficiency metric measuring expected time per qualified candidate. In this study, the system improves throughput and achieves 1.70 hours per qualified candidate versus 3.33 hours for the experienced recruiter, with substantially lower estimated screening cost, while preserving a human decision-maker as the final authority.