RAG-Enhanced AI Talent Acquisition Platform

Traditional recruitment is often inefficient, manual, and biased, resulting in delays and inconsistent outcomes. This paper presents an AI-assisted Talent Acquisition Platform that streamlines the recruitment lifecycle from job posting to onboarding through automation and system integration. Leveraging WorqHat APIs, the platform enables advanced natural language processing for resume parsing, contextual job matching, and candidate shortlisting without in-house model training. To enhance reliability and reduce LLM hallucinations, a Retrieval Augmented Generation (RAG) pipeline is integrated: candidate profiles and extracted resume contents are embedded into a vector store, and top-K relevant records are retrieved as grounded context for the WorqHat LLM. This hybrid retrieval + LLM approach ties outputs to verifiable candidate data and scales efficiently for large applicant pools. Built with React.js, Node.js, and Firestore, the system also supports interview scheduling and real-time email communication, achieving a reduction in time-to-hire and improved candidate-job matching accuracy.