An area ripe for using Artificial Intelligence is multimodal analysis. The main aim of this project is to develop a multimodal interviewer which is capable of understanding verbal cues such as lexical features as well as non-verbal cues such as facial expressions and tone. The application will provide an intuitive and user-friendly bot that is capable of interviewing the candidate on behavioral questions in Human Resources (HR) rounds. It also generates a report to the user based on facial expressions, tone, and text, which is crucial feedback on the candidate’s performance. The audio model achieved a training accuracy of 86.67% and a test accuracy of 79.24%. The facial expression emotion recognition model achieved a training accuracy of 67.9% and a test accuracy of 60%. Our focus remains specifically on optimizing interview experiences and outcomes within the HR domain.