The employment market in today’s modern society is growing increasingly active, which makes choosing a clear opportunity for yourself a difficult endeavor, particularly for newcomers who are unfamiliar with the numerous possible professions. As a result, the need for employment recommendation systems has been steadily increasing. Many systems employ suggestions to provide consumers with personalized solutions. By examining job recommendation articles, we are taking into account various machine learning algorithms as well as models provided in this study. The information in the student’s résumé is compared to the specifications of the job opportunities. Users’ abilities, knowledge, past previous employment, demographic data, as well as other necessary details are extracted from recommendation apps. The applicant is presented with fresh positions that are unrelated to the one being sought based on the extraction of information. We discovered that by using content-based filtering to unsupervised based on deep learning classification methods such as SVM, KNN, and randomized forest, the random forest approach delivers the highest outcomes for our applications. Python is used to construct the recommendation engine.