Unemployment is a serious concern around the world. Every year, millions of graduates are without a job. Students enrol in graduate schools without understanding what the job market expects. Upon graduation, the necessary skills to secure employment are often lacking. In such instances, it can be inferred that degree programmes fail to prepare students for job applications and interviews. A framework must be in place to educate graduates about available employment. Hence a job recommender system comes into the picture. Its main objective is to recommend jobs to students based on technical skillset, logical quotient rating, self-learning capability and a variety of other criteria. The system can also serve as feedback for programmes as it gauges the employability of the student passing out. It can also be used by regulatory councils (government organizations like AICTE which regulate and approve technical programmes) to decide whether the programme should be continued based on the number of job-ready graduates produced. The proposed work has employed classifier algorithms (machine learning), for categorizing student placement data based on features like ‘Academic Percentage in Operating Systems’, ‘Percentage in Computer Networks’, ‘Hours working per day’, etc. The performance of various classifiers is also analyzed.