Blue River Technology (John Deere) - Data Platform

As a founding member of the data platform team, I helped build and scale the storage layer, REST API, ingestion pipelines, labeling service integrations, and dataset management using Python, Docker, AWS (S3, ECS, RDS with PostgreSQL), and MongoDB.

I supported onboarding of new autonomy project teams and scaled platform services as annual data collection grew to more than 250 million images.

I prototyped a near–real-time machine metrics alerting and visualization stack for debugging robotics issues using AWS IoT, Kinesis, S3, DynamoDB, and Grafana.

I delivered an integrated data warehouse on AWS S3, Glue, and Athena for business analytics and ad-hoc exploration on image datasets with up to about 500 million records.

I deployed and maintained Kubeflow on AWS EKS for platform and project teams to orchestrate pipelines and host notebooks for ML and analytics.