Optical Character Recognition Experts in Germany

Led the end-to-end integration and migration architecture for decommissioning SAP IS-U market communication and transitioning to Salesforce Marketing Cloud (SFMC) with E.ON IT Services — covering regulated EDIFACT market messaging, a three-phase data migration (transfer of market message inventory after cutover), redesign of market communication processes, and full GDPR and German energy-market compliance.

• Designed the three-tier target architecture (SAP IS-U → NScale B2B gateway → SFMC) processing 50,000–100,000 EDIFACT messages daily within sub-5-minute SLAs.
• Architected the three-phase data migration: 36 months of historical data, zero-loss cutover of in-flight market messages, and near-real-time CDC synchronization.
• Delivered secure, BDEW/GDPR-compliant integration (AS2/OFTP2, RFC/IDoc, REST APIs, OAuth 2.0, Azure AD, AWS S3) achieving >99.5% uptime, <0.1% migration discrepancy, and RTO <4 hours.
• Applied BPMN to model and optimize the market communication processes.

Technologies: SAP IS-U, NScale, Salesforce Marketing Cloud, EDIFACT, OAuth 2.0, Azure AD, AWS S3, BPMN, Jira, Confluence, Draw.io

• Designed and developed a production-ready data platform based on Microsoft Fabric for an e-commerce company
• Built a scalable Medallion Architecture (Bronze, Silver, Gold) with Lakehouse and Delta Lake as the foundation for analytics and AI applications
• Developed a metadata-driven ETL platform with PySpark and a generic Incremental Loading Framework (SQL Server → Bronze → Silver → Gold)
• Developed reusable components for Microsoft Fabric Notebooks to standardize data integration, transformation, and validation
• Implemented automated data pipelines including monitoring, logging, error handling, and Delta MERGE strategies for stable production operations
• Built a business layer architecture for reporting, data warehousing, and reusable data products
• Integrated heterogeneous data sources via SQL Server, REST APIs, Amazon SP API, and Google Analytics 4
• Worked closely with business departments to analyze business requirements and translate them into scalable data architectures

Technologies: Microsoft Fabric, PySpark, Python, SQL Server, Delta Lake, Lakehouse, OneLake, Data Factory, Data Warehouse, REST APIs, Amazon SP-API, Google Analytics 4

• I support medium-sized clients with their funding needs.
• I evaluate operational business processes and translate complex legal and regulatory requirements into business requirements, target models and actionable roadmap epics.
• I use Generative AI tools and automation in a targeted way to efficiently create requirements documentation, process analyses, evaluations, meeting preparation materials, customer analyses and decision papers.

• Taught ML, BI, and Big Data to Master's students.

Tech: Python, Power BI, SQL, ML, SnowflakeDB, databricks, MS Fabric, MongoDB, LLM

AI-supported document processing and inventory management integration

Design and development of an AI-supported application for the automated processing of delivery and invoice documents, connected to SelectLine ERP. Documents are analyzed using AI, matched with orders and line items, and prepared for posting goods receipts.

IMPACT:

• Automated extraction of structured order, delivery and invoice data from PDF and image documents
• Automatic and manual mapping of documents to orders and order line items
• Integration with SelectLine ERP for order import, status synchronization and goods receipt postings
• Traceable processing through separate analysis, mapping and posting processes as well as technical logging
• Development of a containerized end-to-end architecture with AI analysis, workflow automation and relational data storage

KEYWORDS: AI, document analysis, OpenAI, n8n, SelectLine ERP, FastAPI, Python, JavaScript, MariaDB, Docker, REST API, PDF, OCR, mapping, inventory management, goods receipt, workflow automation

The program supports the comprehensive realignment of the German Consumer Panel Services business. It combines a significant panel boost with the reprocessing of historical data and the integration of new receipt data. By significantly expanding and stabilizing the panel with the involvement of external partners, the aim is to improve the validity of the data base and create a reliable foundation for methodology, weighting and customer reporting. At the same time, historically grown processes for data delivery, OCR, matching, item QC, methodology and reporting are being harmonized, further developed technologically and reorganized. The goal is a scalable end-to-end landscape with higher data quality, clear responsibilities, reliable governance and sustainably manageable operational processes.

• Overall management of the restatement program, including the integrated roadmap as well as milestones, dependencies, risks and management decisions.
• Coordination of the panel boost and alignment of the required data deliveries, quality requirements and prerequisites for methodology, weighting and reporting.
• Alignment of business, product, data science, technology, operations and external partners around a shared target picture, aligned priorities and an integrated approach.
• Design of the organizational change triggered by the fundamental realignment of the data base, methodology and management logic, which has a lasting impact on established decision-making and collaboration patterns.
• Establishment and further development of governance, reporting and escalation structures as well as program-wide monitoring and operational processes for reliable management and sustainable handover.
• Management of critical data, technology and provider dependencies, including reprocessing, OCR transition and the timely synchronization of delivery, testing, methodology and reporting.
• Orchestration of international collaboration with teams and stakeholders in Germany, the United Kingdom, Portugal and Romania, as well as with external suppliers in Germany and Austria.

Impact Areas and Expertise: Program & Delivery Leadership, Business & Technology Alignment, Organization & Transformation, Governance & Sustainable Operations, Strategy & Target, Methodic Leadership, Transformation & Change Leadership, Executive Advisory

• Owning RAG, LLM-System, ML-ops-Pipelines for various startups in Insurance, Banking, Energy (KRITIS)

Multi-Agent Document-Generation Platform

Problem:

Turn a single prompt into a well-researched, structured and cited document, while keeping the user in control: every stage can be reviewed, corrected or revisited before the system moves on.

Architecture:

A multi-agent system orchestrated by a central controller. More than 20 specialised pydantic-ai subagents (understanding, structuring, planning, research, writing, assembly, cross-reference check, glossary, citation, reference table and more) pass results forward through a shared plan persisted in Postgres (asyncpg); a runner layer dispatches each task by name to its agent, and mechanical steps such as formatting, table of contents and list of figures are deterministic code instead of LLM calls. Provider (Anthropic or OpenAI) is a configuration setting, and responses stream over Server-Sent Events.

Hosting & Infrastructure:

Stateless container run as a Scaleway Serverless Container on a private network with managed PostgreSQL, object storage for finished documents and assets, and centralized log shipping (Loki / Scaleway Cockpit), provisioned with OpenTofu modules and deployed through GitLab CI; usage is metered per API key.

My Contribution & Key Decisions:

• Central decision controller: a satisfaction classifier turns the user's free-text feedback into a verdict (keep working, advance, cancel or revise an earlier task), and a middleware applies it to the plan. Plan progression supports jumping back to earlier tasks and re-running the stages after them.
• Research and writing fan-out: planning produces a plan from which a research-design agent generates individual research tasks and a writing-design agent generates individual writing tasks, each linked to the research it needs. Every task runs in its own dedicated agent with its own conversation history.
• Self-review and human-in-the-loop: after each step a critical-thinking agent reviews the output; the user can accept, refine, or ask questions about a critique before the plan advances.
• MCP integrations: two remote MCP servers, web search and internal document search, connected through pydantic-ai with retries and long-running tool-call timeouts. Classifier agents decide per task whether web search is needed, and a small model condenses raw search results into structured findings before they reach the writing agents.

Usage Metering:

Clients authenticate with an API key validated against a key-management service; consumption is charged in credits calculated from token usage per model plus a markup, and exhausted quota is answered with HTTP 429.

• This project involved extraction of intelligence data to support report writing for a company that provides geopolitical, global, commercial intelligence. The data have been gathered from a number of resources (interview transcripts, online data, internal documents), and then a knowledge base has been build from it. This was the basis of a complex RAG system, that was evaluated against a golden dataset. Agents have been used to find out the contradicting intelligence, the statements supporting each other, and to store back the generated knowledge.

Used: Python, RAG, LangGraph, LangChain, deepeval, MCP

• Objective/Motivation: PAYONE urgently needs a 360° view of its customers. So far, PAYONE has had no company-wide master data strategy. It is not possible to identify customers across all relevant systems.

The organization is to be enabled to identify customers across all relevant systems. Establishing the basis for master data management at PAYONE

• Challenge: Due to company acquisitions, the system landscape is very heterogeneous. The company is highly dynamic and burdened with many system harmonization and integration projects, meaning that resource bottlenecks and changes in project priorities repeatedly create an almost impossible task.

Due to BaFin findings, the project has a central task and role. The first focus is the migration of all customers, including their AML/KYC data, from the master data backend systems to Salesforce. This is intended to resolve one of the largest findings and establish the corresponding ODD/EDD processes.

In addition, customer data must be harmonized in Salesforce. Previous migrations resulted in duplicate customer records in some cases. The aim is therefore to maintain only one customer in Salesforce and, using the relevant information from the backend systems, also be able to identify which products the customer uses and in which processing systems the customer obtains PAYONE services.

Project: ONE Customer

Budget: €1.5 million

Team: 10/30 employees (full-time/part-time); 4 vendors/providers

Integration: 8 (subsystems/interfaces)

Applications: Salesforce; SAP S4/HANA; in-house developments

Tools: MS Office; Jira, Confluence, SharePoint

Methods: Hands-on; Agile (SAFe); Prince2

• Led a 16-person finance and accounting organization during a restructuring phase; strengthened closing discipline, financial control, cash transparency and accountability.
• Supported cost programs with approximately €2 Mio. in annual savings; established regular KPI reviews for P&L, working capital, POC and cash topics.
• Responsible for monthly, quarterly and annual closing under HGB/IFRS, management/group reporting, audit, tax and GoBD compliance.
• Finance automation with clear business benefits: 13-week liquidity planning, cash flow reporting, P&L versus plan, variance analysis and bank reconciliation; reduced manual work by 40–60 %.
• Improved accounts payable processes through OCR-supported invoice processing and three-way matching with exception handling.
• Sparring partner to management on restructuring, liquidity, working capital, risks and process simplification.

• Interim PO for a DiGA-listed digital therapy platform, ensuring compliant product development in a highly regulated SaMD environment (BfArM, BSI) while maintaining delivery pace.
• Challenge: Regulatory complexity combined with hands-on delivery responsibility and only one week of onboarding time.
• Impact: Introduced AI-assisted product development workflows with clear quality standards and reinstated regular short release cycles for faster, more precise delivery. Currently optimizing product development workflows and reducing AI-generated bloat in tickets and documentation.
• Introduced an OCR-based workflow in Langdock that automates therapy plan creation from prescription images.

• Designed and developed a multi-tenant SaaS platform enabling organizations to build their own knowledge bases and chat with brand-customized AI assistants (white-label approach with dynamic branding per organization).
• Implemented a scalable RAG architecture with a GPT-4o tool-use loop, hybrid semantic search, and strict tenant isolation at database and search index level.
• Built persistent, project-like chat sessions including a streaming API (SSE), multilingual support, and speech input/output (STT/TTS).
• Delivered the cloud infrastructure as Infrastructure-as-Code, fully automated per-customer CI/CD pipelines, and an onboarding process for new tenants.

Technologies used: Python, FastAPI, Pydantic (v2 noted), Next.js, React, TypeScript, Tailwind CSS, OpenAI / LLMs (GPT-4o), Azure AI Search, Cosmos DB, Azure Blob Storage, Azure Cognitive Services Speech, Azure App Service, Azure Container Registry, Retrieval-Augmented Generation (RAG), Server-Sent Events (SSE), Docker, Terraform, GitHub Actions, REST, OpenID Connect (OIDC), Multi-Tenancy

Designed and developed an Azure-based AI and data platform transforming distributed project documents into searchable, structured knowledge for an enterprise AI assistant. Combined incremental document processing, hybrid keyword/vector retrieval, knowledge graph extraction, and conversational AI for Microsoft Teams and Microsoft 365 Copilot. Implemented Python document-processing pipelines for PDF, Word, Outlook and text files; Azure Cosmos DB lifecycle management; Azure AI Search; Azure AI Foundry and Azure OpenAI; identity-aware retrieval with Microsoft Entra ID; project authorization; a TypeScript Microsoft Agents SDK agent; Pulumi infrastructure; resilient scheduling, retry and diagnostic tooling. Technology stack: Python, TypeScript, FastAPI, Pydantic, Azure AI Foundry, Azure OpenAI, Azure AI Search, Azure Cosmos DB, Blob/Table Storage, Container Apps/Jobs, Service Bus, Key Vault, Entra ID, Docker, Pulumi, pytest, Microsoft Teams and Microsoft 365 Copilot.