Cryo-electron tomography is a powerful biophysical technique enabling three-dimensional visualization of complex biological systems. Macromolecular targets of interest identified within cryo-tomograms can be computationally extracted, aligned, and averaged to produce a better-resolved structure through a process called subtomogram averaging (STA). However, accurate alignment of macromolecular machines that exhibit extreme structural heterogeneity and conformational flexibility remains a significant challenge with conventional STA approaches. To expand the applicability of STA to a broader range of pleomorphic complexes, we developed a user-guided, focused refinement approach that can be incorporated into the standard STA workflow to facilitate the robust alignment of particularly challenging samples. We demonstrate that it is possible to align visually recognizable portions of multi-subunit complexes by providing a priori information regarding their relative orientations within cryo-tomograms, and describe how this strategy was applied to successfully elucidate the first three-dimensional structure of the dynein-dynactin motor protein complex bound to microtubules. Our approach expands the application of STA for solving a more diverse range of heterogeneous biological structures, and establishes a conceptual framework for the development of automated strategies to deconvolve the complexity of crowded cellular environments and improve in situ structure determination technologies.