In this paper, we explore the impact of workers' tenure on firm productivity, using rich longitudinal matched employer-employee data on private Belgian firms. We estimate a production function augmented with a firm-level measure of tenure. We deal with endogeneity, which arises from unobserved firm heterogeneity and reverse causality, by applying a modified version of Ackerberg et al.'s (2015) control function method, which explicitly removes firm fixed effects. Consistently with recent theoretical predictions, we find that tenure exhibits an inverted-U-shaped relationship with respect to productivity. The existence of decreasing marginal returns to tenure is corroborated in our analysis on the tenure composition of the workforce. We also find that the impact of tenure differs widely across workforce and firm dimensions. Tenure is particularly beneficial for productivity in contexts characterized by a certain degree of routineness and lower job complexity. Along the same lines, our findings indicate that tenure exerts stronger (positive) impacts in industrial and high capital-intensive firms, as well as in firms less reliant on knowledge- and ICT-intensive processes.