Harsh Rana
Software Engineer @JPMorganChase
Signup · Get unlimited contacts
WORK HISTORY
Software Engineer @JPMorganChase
Noida, IN
Built and maintained ML serving platforms using Python scoring hundreds of transactions per second with a p90 latency of 40msDeployed Catboost ML models to score large payments for potential fraud alerting on millions of dollars of potential fraud per month Worked with product managers and data scientists to support new machine learning algorithms and automated retraining to improve detectionCoordinated with production management teams to define metrics, alarms, and run books to maintain a return to operation within 2 hoursProvisioned AWS EKS and ECS applications and RDS and DDB tables using Terraform IaC for better environment consistency Utilized Cloudwatch metrics to monitor application health and optimize services to reduce operational costs Design, implement, and deploy infrastructure for deploying Machine Learning models.
EDUCATION
Bharat Institute of Technology, Meerut
Bachelor of Technology - BTech
ABOUT HARSH RANA
Built and maintained ML serving platforms using Python scoring hundreds of transactions per second with a p90 latency of 40msDeployed Catboost ML models to score large payments for potential fraud alerting on millions of dollars of potential fraud per month Worked with product managers and data scientists to support new machine learning algorithms and automated retraining to improve detectionCoordinated with production management teams to define metrics, alarms, and run books to maintain a return to operation within 2 hoursProvisioned AWS EKS and ECS applications and RDS and DDB tables using Terraform IaC for better environment consistency Utilized Cloudwatch metrics to monitor application health and optimize services to reduce operational costs Design, implement, and deploy infrastructure for deploying Machine Learning models.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.