Semi-crystalline polymers are a class of polymers which are used in applications ranging from piping to photovoltaics to food packaging. Despite their near-ubiquitous use, our understanding of semi-crystalline polymer microstructure and its connection to mechanical properties is far from complete. While measuring the mechanical properties of material systems using Molecular Dynamics simulations is routine, generating the initial conditions for semi-crystalline polymers is difficult due to their non-equilibrium, kinetically trapped nature. In this contribution, I discuss the development of a python-based simulation tool which uses an adapted Configurational Bias Monte Carlo technique to “grow” coarse-grained representations of semi-crystalline polymer systems. Specifically, I will discuss the process of developing a performant and flexible simulation tool for materials simulation using various tools in the python ecosystem including NumPy, Cython, VTK, and various profiling tools.