The traditional design process for aluminium alloys has primarily relied on iterative alloy production and testing, which can be time-consuming and expensive. Machine learning has recently shown promise in predicting alloy properties based on the inputs of alloy composition and processing conditions. Inverse design of alloys using machine learning has primarily utilised forward machine learning models in combination with a search algorithm or an optimisation method. In this study, we employ an inverse design workflow that uses multi-target machine learning to directly map mechanical properties to alloying concentrations and processing conditions, eliminating the need for external search or optimisation. We further analysed the inverse model and validated its predictions against alloys reported in the literature.