Jack Lopez
← Back to Work
AI/MLAWSPythonReact

GE VERNOVA · EFFECTUAL / AWS PROSERVE

AI Architect & Senior Engineer

Architecture

EngineeringDocumentsClaude VisionAWS BedrockPython / FlaskData ServicesAPM PlatformGE VernovaPDF · DrawingsExtract · ClassifyTransform · EnrichEnterprise Scale

The Problem

GE Vernova's global industrial Asset Performance Management platform contained decades of engineering knowledge locked in PDFs, CAD drawings, and unstructured documents. Extracting and operationalizing that data at scale required a new AI-native approach.

What I Built

  • Integrated Claude Vision via AWS Bedrock to extract structured data from complex engineering drawings and maintenance documents

  • Built Python/Flask microservices to transform extracted data into normalized records for the APM platform

  • Designed the end-to-end pipeline architecture: document ingestion → AI extraction → validation → platform sync

  • Collaborated with GE Vernova engineers to define schemas, edge cases, and acceptance criteria

Outcomes

01

Unlocked document intelligence at enterprise scale across GE Vernova's global APM platform

02

Reduced manual data entry time dramatically by automating extraction from engineering documents

03

Established a reusable AI pipeline pattern for future document-intelligence use cases

At a glance

Role

AI Architect & Senior Engineer

Stack

AI/MLAWSPythonReact

WORKING ON SOMETHING SIMILAR?

I'd like to hear about the problem you're trying to solve.

Get in touch →