In the nowadays modern digital era, the overwhelming amount of available online data has established challenges for individuals seeking personalized educational and career pathways with relevant skill dependencies, especially when surfing e-learning and online recruitment platforms. This challenge emphasizes the need for novel advancements in knowledge-enhanced Recommender Systems, offering more personalized, accurate, and timely recommendations. Recently, the rapid development of Large Language Models (LLMs) with their broad knowledge and complex reasoning skills, has significantly enhanced the ability of these systems to offer precise and knowledge-based suggestions. It highlights their potential to enrich these systems using their vast amount of knowledge and sophisticated reasoning capabilities, to leverage them as an alternative to structured knowledge bases like knowledge graphs (KGs). However, LLMs have still limitations for knowledge-based content generation, especially when it’s a domain-specific case. To address this issue, researchers propose to enhance the system with explicit factual knowledge from KGs. This research aims to explore advanced technological developments in knowledge-enhanced conversational Recommender Systems to propose a novel system, named AIREG for the educational and career development sectors.