Both short‐acting (epoetin alfa or beta) and long‐acting (darbepoetin alfa or PEG‐epoetin) erythropoiesis‐stimulating agents (ESAs) are commonly prescribed for patients with kidney failure undergoing maintenance hemodialysis. We compared the risks of major adverse cardiovascular events (MACE) and of all‐cause mortality associated with receipt of short‐ vs. long‐acting ESAs. This retrospective cohort analysis included Medicare hemodialysis beneficiaries aged ≥ 18 years in the United States Renal Data System from January 2015 to December 2017. We included adults who survived > 90 days after initiating hemodialysis and received either short‐ or long‐acting ESAs. Outcomes were MACE (first occurrence of stroke, acute myocardial infarction, or cardiovascular‐related mortality) and all‐cause mortality. After stabilized inverse probability of treatment weighting, Cox proportional hazards regression models were used to estimate the hazard ratio (HR) and 95% confidence interval (CI) for each outcome. Of 68,607 patients (mean age: 65 years, 45% females), 33,658 (49%) received long‐acting ESAs and 34,949 (51%) received short‐acting ESAs. There was no difference in the risk of MACE associated with receipt of short‐ vs. long‐acting ESAs (HR: 1.02 (95% CI: 0.98–1.08)). However, long‐acting (vs. short‐acting) ESA receipt was associated with a lower risk of all‐cause mortality (HR: 0.91 (95% CI: 0.87–0.96)). Compared with short‐acting ESAs, long‐acting ESAs were associated with a lower risk of all‐cause mortality, with no difference in the risk of MACE. Future studies with a longer follow‐up are needed to confirm these findings.