Purpose We evaluated the potential associations between the consumption of ultra-processed food (UPF) and the incidence of obesity among Uruguayan and Brazilian preschoolers. Design and methods We conducted a longitudinal analysis using data from preschool children from Uruguay and Brazil. The “Health, child development and nutritional survey” (ENDIS) was conducted in Uruguay in 2013–2014 and 2015–2016. The Brazilian survey (Pelotas 2015 Birth Cohort) has measures from 2017 and 2019. The main outcome measure was obesity defined as body mass index (BMI) for age and sex ≥ +3 z-scores. The score of UPF consumption was the main exposure measured. Multilevel crude and adjusted Poisson regressions were performed to estimate risk ratios and the respective 95% Confidence Intervals (95% CI). Results The overall incidence of obesity in this group of young Latin-American children with a mean age of 48 months was 4.1%. We observed a relationship between UPF and obesity with statistical significance (RR: 1.10 (95% CI, 1.02–1.18). Adjustment for weight at birth, age, sex, breastfeeding, country, and time between waves resulted in a similar relationship but lack of statistical significance. Conclusions Whilst in this study we did not find strong evidence of an association between the incidence of obesity and the intake at baseline and currently of UPF, results suggest that higher UPF consumption is more favorable than reduced consumption for the development of obesity. Practice implications: The present study reinforces the importance of nutrition education and more effective public policies for promoting healthier food choices in early childhood.