How Jumio built a real-time feature store on AWS
Jumio built a sub-100ms real-time feature store on AWS for fraud detection ML models
Jumio, an identity verification provider, solved fragmented ML feature engineering by building a centralized real-time feature store on AWS using SageMaker Feature Store, Apache Flink, and Kinesis Data Streams. The architecture achieves sub-100ms latency required for fraud detection and eliminates the manual re-implementation of offline features in production code. This is a practical MLOps case study rather than a headline AI industry signal.