The generation of molecules with artificial intelligence (AI) or, more specifically, machine learning (ML), is poised to revolutionize materials discovery. Potential applications range from development of potent drugs to efficient carbon capture and separation technologies. However, existing computational discovery frameworks for polymer membranes lack automated training data creation, generative design, and physical performance validation at meso-scale where complex properties of amorphous materials emerge. The methodological gaps are less relevant to the ML design of individual molecules such as the monomers which constitute the building blocks of polymers. Here, we report automated discovery of complex materials through inverse molecular design which is informed by meso-scale target features and process figures-of-merit. We have explored the multi-scale discovery regime by computationally generating and validating hundreds of polymer candidates designed for application in post-combustion carbon dioxide filtration. Specifically, we have validated each discovery step, from training dataset creation, via graph-based generative design of optimized monomer units, to molecular dynamics simulation of gas permeation through the polymer membranes. For the latter, we have devised a representative elementary volume (REV) enabling permeability simulations at about 1000× the volume of an individual, ML-generated monomer, obtaining quantitative agreement. The discovery-to-validation time per polymer candidate is on the order of 100 h using one CPU and one GPU, offering a computational screening alternative prior to lab validation.