Enhancing the hydrogen embrittlement (HE) resistance of alloys caters to the urgent needs of engineering safety and long-distance hydrogen transportation. Highly dense precipitates present in the microstructure of alloys act as H traps, however, some of them cannot strongly trap H thus failing to prevent its accumulation at the critical regions (e.g., crack tip, etc) resulting in the material’s rapid failure. Experimentally, it is challenging to expeditiously identify and generate phases causing strengthening and acting as strong H traps. Here, we demonstrate a computation-based design strategy to generate precipitates strongly trapping H, decreasing the HE susceptibility of Al alloy (by ~78%) by tuning the Cu distribution in the microstructure. Our density functional theory results show that the Cu-doped Al3Sc exhibit strong Cu-H bond. The quantum machine learning Al-Sc-Cu potential, developed within this study, aids in rapidly determining the optimal processing parameters to create phases that can strongly trap H even though they are metastable in nature. Our modelling approach provides insights into the underlying mechanisms behind precipitation. Elemental mapping in the electron microscope confirms the presence of Cu in Al3Sc, which exhibits a more deeply trapped H peak than dislocations in the H desorption curve. Hence, we envisage the proposed strategy will accelerate the design of HE-resistant microstructures of various technologically relevant materials via identification of desirable phases.