Career selection is a key concern for all students to decide a suitable field of study after completion of high school. Students sometimes feel hesitant to make the right choice when it comes to their specialization because it directly impacts their future careers. Knowing the student’s interests and academic background will help in selecting their job role properly. In this research, we suggested an Expert System for Student Career Prediction (ESSCP) model based on machine learning techniques to suggest the job roles they should pursue in their career. In this study, five algorithms—two standalone classifiers and three ensemble classifiers were used. The dataset utilized for this work was collected from “Github,” which predominantly contains null values. Data imputation has been done using K-nearest neighbor and Multivariate Imputation using Chained Equations. According to the findings, XGBoost performed superior than all the other classifiers in terms of accuracy and kappa score. Tenfold cross-validation was engaged in conjunction with the 70:30 train-test split to validate the performance. The greatest accuracy for MICE with a 70:30 split was 92.31%, while it reached 92.07% for tenfold cross-validation. Although the findings are extremely encouraging, testing with more real-world datasets will correctly evaluate the model’s performance.