The exponential growth of Internet allowed the development of a market of online job search sites. This paper aims at presenting the E-Gen system (Automatic Job Offer Processing system for Human Resources). E-Gen will implement several complex tasks: an analysis and categorization of jobs offers which are unstructured text documents (e-mails of job offers possibly with an attached document), an analysis and a relevance ranking of the candidate answers. We present a strategy to resolve the last task: After a process of filtering and lemmatisation, we use vectorial representation and different similarity measures. The quality of ranking obtained is evaluated using ROC curves.