Accurate photometric redshifts are necessary for mapping the three-dimensional structure of the universe, allowing us to test models of cosmology and galaxy evolution. To prepare for the beginning of the Vera C. Rubin Observatory's Legacy Survey of Space and Time, the Dark Energy Science Collaboration (DESC) launched a photometric redshift (photo-z) estimation challenge in spring 2026. At that time, all existing photo-z estimation methods had a redshift uncertainty larger than limits outlined in the official DESC Science Requirements. In this talk, I present Cin-zs, a machine learning-based approach for photo-z estimation submitted by our group as part of this challenge. I report on the performance of our algorithm when applied to Tasksets 1 and 2 and outline possible avenues for improvement when extending to Tasksets 3 and 4.