ML Engineer · Istanbul
Sarah Ilyas
I design and build production ML pipelines — from drift detection to automated retraining. Currently working on agricultural yield forecasting at scale.
PythonXGBoostMLOpsFastAPIDockerAWS
Sarah Ilyas
ML Engineer
Recent articles
View all →Prediction intervals vs confidence intervals: why confusing them will break your production model
May 12, 20268 min readstatisticsmlops
Prediction intervals are more useful than point estimates
May 5, 202611 min readxgboostuncertainty
Building a self-healing ML pipeline
Apr 28, 202613 min readmlopsdrift
Featured projects
View all →🌿
Cropcast
Production ML pipeline for agricultural yield forecasting across 13 countries.
xgboostmlopsfastapidocker