Career guidance is a profession that takes place to assist the people with information, advice and guidance in order to help them make decisions regarding their education, training, skill development and future career. Individualized career counseling also enhances the process by matching each person with his or her objectives and professional experiences. Although the availability of digital information is increasingly growing, it is done in a huge volume of data that cannot be managed by traditional approaches of offering personalized career guidance. Nevertheless, artificial intelligence (AI) applications have been shown as capable of filtering through large amounts of data to provide extremely relevant and accurate suggestions to individual users. The ever-increasing number of various academic programs and the dynamism of industry skills has necessitated the high demand of smart digital career advice websites. The conventional method of counselling is also restricted by human resources, subjectivity and the failure to process vast data. To overcome them, Career Nova is offered as an AI-based, scalable, and interactive counselling service, which provides a personalized career advice, real-time guidance, and skill-gap insight to learners. The system will incorporate machine learning models of profile-based recommendation, artificial intelligence powered chatbot of natural language based interactive counselling and secure data management layer of managing user information. Quantitative experiments using anonymized datasets of students prove that the proposed model is accurate in predicting appropriate career areas 88%–90%. The paper outlines the entire architecture, methodology, evaluation results, and future enhancements on the basis of reviewer feedbacks, discussions on performance, reliability, scalability and future improvement. The paper contains a personalized AI-driven career counseling system which mitigates the limitations of the conventional methods. The approach employed a formal waterfall in order to ensure that the design, development, and testing stage was undertaken in a methodical way. The recommendations engine proved to be flexible as it provided customized career recommendations to user profiles.