Salmonella is a common food-borne pathogen with Enteritidis and Typhimurium being among the most important serovars causing numerous outbreaks. A rapid method was investigated to identify these serovars using whole-cell MALDI-TOF MS coupled with multivariate analysis and artificial intelligence and 113 Salmonella strains, including 38 Enteritidis (SE), 38 Typhimurium (ST) and 37 strains from 32 other Salmonella serovars (SG). Datasets of ions (presence/absence) with high discriminative power were created using newly developed criteria and subject to multivariate analyses and eight artificial intelligence (AI) tools. Principal Component Analysis based on 55 or 88 selected ions separated SE, ST and SG without overlap on the first three principal components. Datasets were partitioned using five partitioning methods with 70% of samples for AI model training and 30% for validation. Of the eight AI models evaluated, high performance (HP) SVM and HP Neural were the top performers, identified three serovar groups 97% correctly on average (range 82%–100%) according to the validation results. Selection of serovar specific ions facilitated differentiation of serotypes using unsupervised model PCA and improved the accuracy of classification using AI significantly (p < 0.01). MALDI-TOF MS incorporated with advanced data processing and classification tools is a promising method to allow rapid identification of Salmonella serovars of concern in routine diagnostic laboratories.