Project Timeline

2023 - 2026

Integrated Large Language Models and Vision-Language Models into production document extraction system, architecting end-to-end AI solution serving enterprise clients.

2024

Promoted adoption of AI coding assistants across the organization, first to integrate GitHub Copilot company-wide.

2022

Architected and integrated self-hosted enterprise RAG system using Langchain (early adoption), vector databases, and agent frameworks to provide intelligent access to company knowledge base.

2021 (2 months)

Migrated entire document processing pipeline from legacy OCR provider to Azure Document Intelligence in 2 months, avoiding 100% price increase while gaining new capabilities.

2020

Designed and trained account line prediction model for automated invoice processing. Project demonstrated technical limitations of pre-transformer architectures for variable-length sequence prediction.

2019

First AI solution integrated at Springtime Technologies - CNN-based field extraction system with custom embedding layer for automated invoice processing.

2019

Built template-based system for extracting table structures from invoices, including multi-line headers.

2018

Designed and implemented semantic rule engine for flexible field extraction using spatial and relational patterns.

2018

Built recommendation system to auto-populate invoice fields based on historical data, reducing manual entry time.

2014 (3 months)

Automated quarterly customer satisfaction reporting for Austria's largest telecommunication provider as part of my bachelor's thesis internship.

2012

3D marble run construction application for scientific assessment of children's cognitive development.