Early prediction of hemodynamic shock in the ICU can save lives. Several studies have leveraged a combination of vitals, lab investigations, and clinical data to construct early warning systems for shock. However, these have a limited potential of generalization to diverse settings due to reliance on non-real-time data. Monitoring data from vitals can provide an early real-time prediction of Hemodynamic shock which can precede the clinical diagnosis to guide early therapy decisions. Generalization across age and geographical context is an unaddressed challenge. In this retrospective observational study, we built real-time shock prediction models generalized across age groups (adult and pediatric), ICU-types, and geographies. We developed generalizable models on publicly available eICU dataset, which is externally validated on cohorts derived from more than 0.23 million patient-hours of vitals data from a pediatric ICU in New Delhi and 1 million patient-hours vitals data from the adult ICU MIMIC-III database. Out of 208 hospitals data of eICU, we found 156 eligible for cohort building and split this data hospital-wise in a 5 fold training-validation-test set. Our model predicted hemodynamic shock 8 hours in advance with AUROC of 86 %(SD= 1.4) and AUPRC of 93% (SD =1.2). Our models identified 92% of all the shock events more than 8 hours in advance. Upon external validation on the MIMIC-III cohort, it achieved an AUROC of 87 %(SD =1.8), AUPRC 92 %(SD=1.6). External validation of our models on New Delhi’s Pediatric SafeICU data achieved an AUROC of 87 %(SD =4) AUPRC 91% (SD=3). Therefore, our models can guide early therapy decisions to save lives, reduce false alarms and address the generalizability gap. Our data and algorithms are publicly available as a pre-configured Docker environment at https://github.com/SAFE-ICU/ShoQPred.