In the present day, employers are discussing difficulties with educated people. The web system posts positions in the authority and recommends various career categories based on skills and qualifications. Those who meet the qualifications for jobs at different organizations or income institutions around the globe are paid more and are promoted over time. Thus, learning about a web-based job suggestion system is crucial in real life. It is necessary to have a crucial dataset with both textual and numerical information in order to classify people who are suggested for jobs and who are not. In this work, we employed a hybrid Kaggle dataset to forecast the job recommendation system through the application of machine learning-based versions of the genetic algorithm. With the help of 11 characteristics and 1000 records overall in the used dataset, a genetic algorithm can identify the top applicants for a job suggestion. The parameters of the fitness function enabled the model to generate the most accurate results. The core components of the suggested system were natural selection approaches, crossover, and mutation tasks. In light of our primary objective is to produce people who are highly qualified for the position and have the highest fitness value. In this work, we proposed a job recommendation system that categorizes candidates into those who are and are not qualified for the position using a genetic algorithm. The model with the best fitness percentage accuracy generates the best schedules.