The ability to link external data to an ESCO occupation concept is an essential building block of this process and it supports drafting new occupations and quality control on existing ones. In this report we touch upon a significant challenge that complicates this process. ESCO is currently supporting 28 languages which requires multilingual machine learning models to connect textual information to the ESCO occupations. This report discusses the multilingual mapping approach that the ESCO team established to support the maintenance of ESCO and applies it to different use-cases for illustrative purposes.