Shear cutting is one of the most used processesProcess in sheet metal forming. Thereby, a critical quality attribute of these processesProcess is the geometry of the produced cutting surface, which is predominantly determined during the design phase. Traditionally, such design processesProcess rely on iterative procedures or the tacit knowledge of staff. In this forward design approach, tool parameters are defined first and the resulting quality of the cut surface is subsequently evaluated. However, such trial-and-error methods are time-consuming and ineffective for achieving consistent surface quality, particularly with advanced high-strengthStrength steelsSteel that exhibit complex material behaviour. In order to overcome these disadvantages, the present study introduces an inverse design methodology for a newly developed punchingPunching processProcess using AIArtificial Intelligence (AI)-based surrogate modelling. Rather than starting from tool parameters, the proposed approach predicts suitable punch design parameters based on desired cutting surface characteristics. For this, various AIArtificial Intelligence (AI)-based surrogate models were trained using a dataset containing surface quality metrics and corresponding punch cutting-edge design parameters. Finally, the trained models were evaluated via conventional FE simulationSimulation.