Imaging-based phenotypic screening of cell-based disease models has become an indispensable tool for modern drug discovery. Despite the growing adoption of high-content screening (HCS), analyzing the complex imaging data produced by these systems can take weeks and typically requires hands-on programming by data scientists. Here we describe a cloud-enabled AI platform for analyzing and visualizing HCS data. The workflow involves importing raw HCS data and experimental metadata to PerkinElmer ColumbusTM Image Data Storage and Analysis system. Experimental control conditions (i.e. disease and healthy wells) are selected in Signals Screening, and a segmentation-free deep convolutional multiple instance learning model is trained to classify entire fields-of-view in the screen based on control treatments. This classifier is then used to score the rest of the treatments screened, typically identifying hits in a drug library. Resulting scores and images highlighting positive phenotypes are displayed in a Signals Screening dashboard.