This thesis comprises the creation of a computer vision-based analytics platform for making age and gender-based inference for retail analytics. Computer vision in retail spaces is an emerging field with interesting opportunities for research. The thesis utilizes modern technologies to create a machine learning pipeline for training two convolutional neural networks for classifying age and gender. Furthermore, this thesis examines deployment and inference computing of the trained neural network models on a Raspberry Pi single board computer. The results presented in this thesis demonstrate the feasibility of the created solution.