Amorphous titanium dioxide TiO2 (a-TiO2) has been widely studied, particularly as a protective coating layer on semiconductors to prevent corrosion and promote electron-hole conduction in photoelectrochemical reactions. The stability and longevity of a-TiO2 is strongly affected by the thickness and structural heterogeneity, implying that understanding the structure properties of a-TiO2 is crucial for improving the performance. This study characterized the structural and electronic properties of a-TiO2 thin films (∼17 nm) grown on Si by atomic layer deposition (ALD). Fluctuation spectra V(k) and angular correlation functions were determined with 4-dimensional scanning transmission electron microscopy (4D-STEM), which revealed the distinctive medium-range ordering in the a-TiO2 film. A realistic atomic model of a-TiO2 was established guided by the medium-range ordering and the previously reported short-range ordering of a-TiO2 film, as well as the interatomic potential. The structure was optimized by the StructOpt code using a genetic algorithm that simultaneously minimizes energy and maximizes the match to experimental short- and medium-range ordering. The StructOpt a-TiO2 model presents improved agreements with the medium-range ordering and the k-space location of the dominant 2-fold angular correlations compared with a traditional melt-quenched model. The electronic structure of the StructOpt a-TiO2 model was studied by ab initio calculations and compared to the crystalline phases and experimental results. This work uncovered the medium-range ordering in a-TiO2 thin films and provided a realistic a-TiO2 structure model for further investigation of structure-property relationships and materials design. In addition, the improved multi-objective optimization package StructOpt was provided for structure determination of complex materials guided by experiments and simulations.