Managing a TB-scale healthcare data lake and deploying machine learning models into production environments.

Data Engineer and MLOPs

Role Overview

As a Systems Engineer for the GE Healthcare Project at TCS, I focus on bridging the gap between data science and live production environments. My work centers on processing massive amounts of healthcare telemetry and ensuring high-availability data for predictive analytics.

Data Engineering & ETL Architecture

• Designed and built ETL pipelines utilizing AWS Glue and Step Functions
• Processed daily incremental data batches efficiently
• Managed and maintained a TB-scale data lake containing highly sensitive CT/MRI telemetry logs and CRM data

MLOps & Production Deployment

• Deployed machine learning models into live production environments using Amazon SageMaker
• Streamlined the handover process between the core data science team and operations
• Automated complex data extraction and preparation workflows to guarantee system reliability