Optical Character Recognition Experts in Germany

• Goal/Motivation: PAYONE urgently needs a 360° view of its customers. So far, PAYONE has no overall 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. Creating the foundation for master data management at PAYONE

• Challenge: Due to acquisitions, the system landscape is very heterogeneous. The company is very dynamic and burdened with many system harmonization and integration projects, so resource bottlenecks and changes in project priorities are again and again almost impossible to handle.

Due to BaFin findings, the project has a central task and role. The first focus is on migrating all customers from the master-data-leading backend systems with their AML/KYC data 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 led in some cases to duplicate customer records. In the end, only one customer should be maintained in Salesforce and, with the corresponding information from the backend systems, it should also be possible to recognize which products and in which processing systems the customer uses 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; custom developments

Tools: MS Office; Jira, Confluence, SharePoint

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

• 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

• Own full-stack development of an AI-native enterprise platform built on TypeScript, React, Vite, tRPC, Hono, and PostgreSQL, delivering AI-powered consulting workflows to B2B clients.
• Designed and shipped a multi-agent AI system using ReAct framework and Claude skills-style workflow patterns, including an intelligent PM assistant with rich system prompts, slash commands, tool integrations, and streaming chat UI.
• Architected an LLM evaluation framework: rubric-based LLM-as-judge, golden datasets, regression testing, and automated quality gating — ensuring consistent AI output quality at scale.
• Integrated LangFuse for end-to-end LLM tracing, conversation replays, and evaluation pipelines, enabling data-driven prompt optimisation that reduced token costs and response variance.
• Built with Drizzle ORM, pgvector, and knowledge graphs for structured data access, semantic search, and relationship-aware AI reasoning across the platform.
• Led TanStack React Query migration across the application — replacing manual state management with centralised caching and automatic refetching, reducing data-fetching boilerplate significantly.
• Practiced AI-native development throughout: Claude Code, Codex, Perplexity SDK, and LLM-assisted testing across the full development lifecycle. Deployed on Vercel + Azure ACA with Biome for linting/formatting.

Manufacturing intelligence platform with enterprise workflows, RAG, real-time AI assistant features, and multi-repository backend architecture.

• Built and extended production AI/backend services with Django, DRF, FastAPI, GraphQL, Celery, PostgreSQL, MySQL, Redis, and WebSockets across a modular multi-repository platform.
• Contributed to ARIS V2, a real-time manufacturing AI assistant using LangChain, LangGraph, MCP tool orchestration, planning/execution flows, OpenAI, AWS Bedrock, Qdrant, and Elasticsearch/OpenSearch-backed retrieval.
• Supported rollout expansion from ARIS V1 in 4 of 17 client production plants to ARIS V2 currently active in 13 of 17 plants, increasing real-world deployment coverage to more than 50% of the client footprint.
• Worked on document-grounded RAG functionality including ingestion, OCR, chunking, embeddings, indexing, retrieval, reranking, and grounded answer generation for industrial workflows.

Stack: Python, Django, DRF, FastAPI, LangChain, LangGraph, GraphQL, Celery, WebSockets, OpenAI, AWS Bedrock, Qdrant, Elasticsearch/OpenSearch, PostgreSQL, MySQL, Redis, Docker.

• Developed a real-time video analytics proof-of-concept for deployment on NVIDIA Jetson edge devices.
• Implemented DeepStream pipelines including object detection, tracking, human pose estimation, face anonymization, and zone intrusion detection.
• Built a Qt/Python demonstration UI interfacing with the AI pipeline via REST APIs.

• Designed and developed AI-powered document processing solutions using Python, OCR, NLP, and Large Language Models (LLMs) to automate extraction, validation, and classification of financial documents, reducing processing time by 75%.
• Built intelligent multi-stage workflow automation pipelines integrating AI services, machine learning models, and enterprise systems to streamline financial operations and improve data quality.
• Developed reusable AI-driven transformation frameworks capable of processing structured and unstructured document formats (XML, CSV, JSON, TXT, DAT) and normalizing them into unified business schemas.
• Designed and developed Python-based REST APIs and backend services supporting enterprise finance applications and high-volume data processing workloads.
• Built scalable data synchronization pipelines between Oracle CFIN and SQL databases, incorporating machine learning models for cash-flow forecasting and AP/AR anomaly detection.
• Architected and deployed Apache Airflow workflows to orchestrate AI-powered data pipelines, automating end-to-end processing from document ingestion through financial system integration.
• Led the migration of critical enterprise integrations from MuleSoft to Python-based services, improving maintainability, performance, and operational flexibility while preserving complete data integrity.
• Managed the full API lifecycle including solution design, implementation, documentation, deployment, monitoring, and production support for mission-critical financial systems.
• Collaborated directly with finance stakeholders to identify business challenges, define solution requirements, and deliver measurable operational improvements through automation and AI-driven workflows.
• Worked closely with cross-functional engineering and business teams to rapidly iterate on features, improve processes, and drive successful adoption of AI-enabled solutions.
• Provided technical leadership through architecture reviews, technology decisions, code reviews, and engineering best practices across integration and automation initiatives.
• Mentored developers, established coding standards, and contributed to improving software quality, maintainability, and delivery effectiveness across projects.
• Provided production support during critical month-end and quarter-close financial processes, performing root-cause analysis and implementing rapid fixes to ensure system reliability and data accuracy.

• Expert-supervised AI systems for scientific reasoning, model evaluation, and research workflows.
• Built the IAS Problem Solver, an orchestrated system for difficult mathematical reasoning; it achieved 84% in one submitted answer set on the Leipzig mathematics benchmark.
• Built a resumable state-machine pipeline for research-grade mathematics benchmark generation: source selection, LLM-agent-based phenomenon discovery, task synthesis, gold-answer and certificate generation and validation, probing, repair, human feedback, and quality gates, targeting tasks that are difficult, natural, verifiable, and cost-effective.
• Current work extends this into budget-aware AI research workflows for real scientific problems with expert review.

Tech stack: Python, OpenAI/OpenRouter-compatible APIs, embeddings, RAG, SQLite.

UEF 3.0 · Semantic Government Overlay (SGO) · Autonomous Systems (UAS / dual use)

• Designed: Semantic Government Overlay (SGO) – AI-guided administration without replacing existing specialist procedures. Read-only semantic layer over registers and specialist processes based on the Federal Information Management (FIM). Decision authority remains with the case worker (architecture principle).
• Developed: Reference architecture with source-backed, derived statements (Executable Ontologies OWL/RDF/SHACL). Technically guaranteed purpose limitation and no-write-path principle in specialist data – auditable, without a central data pool.
• Anchored: Regulation as a design principle: EU AI Act (high-risk obligations for public-sector AI, fundamental rights impact assessment under Art. 27), GDPR, NIS2, and administrative automation limits (§ 35a VwVfG, § 31a SGB X) as technical control points in the architecture.
• Created: Methodical tool for pilot organizations: data pipeline assessment (phase 0), compliance blueprint, and management summary as a decision-ready package for public administration.
• Specified: UEF 3.0 as a successor architecture to TOGAF – decision paper, canonical ontology, six-layer architecture, read/actuate boundary, federation registry, terminology concordance, and release delta as a closed specification status.
• Architected: AI-native mission OS for autonomous UAS and ground robotics as a tactical layer on top of a separately approved autopilot. Run-time assurance according to ASTM F3269-21 (Simplex pattern): the verified safety controller keeps authority, the AI function provides suggestions.
• Designed: Three-tier architecture – Tier 0 autopilot with 650 Hz flight control on RTOS, Tier 1 AI OS with semantic world model and multi-agent cluster, Tier 2 swarm and ground mesh. Zenoh as the primary fabric, MAVLink as the only authenticated command path (single writer). Result: graceful degradation – loss of the mission, not of the aircraft.
• Secured: Two-gate chain on the read/actuate boundary – governance gate (can-question: AI Act risk class per actuation, enforced human oversight under Art. 14, immutable log) before the RTA safety monitor (is-it-correct question: flight envelope, geofence, energy reserve) with revert to the baseline controller.
• Anchored: Dual-use architecture with common core and build-time fork instead of runtime switch. Three separate legal levels: civil variant – UAS under the EASA Basic Regulation (EU) 2018/1139 with the limited applicability under Art. 2(2) of the AI Act, ground robotics under the Machinery Regulation 2023/1230 with the full high-risk obligation chain, Cyber Resilience Act for both; unarmed carrier variant as defense material under AWG/AWV and Dual-Use Regulation 2021/821 (BAFA approval); armed variant under KrWaffKontrG. Each variant lives under exactly one dominant legal regime. Evidence base: AI BOM, SBOM, and complete data lineage.
• Analyzed: System analysis and realignment of grown engineering system landscapes. Approach concept for consolidation without migration – semantic layer over the existing sources instead of data transfer. Result: decision-ready implementation concept including an evaluation model for the target architecture.

• Automotive SPICE®: all assessments fully achieved
• Agile transformation: V-model → SAFe successfully implemented
• Series release: on-time, quality-assured software delivery for key Volkswagen Group models (including ECE homologation)
• Stakeholder management: internal & external
• Process optimization: implemented a continuous improvement process (CIP) with a tracking system

• Built a JTBD-based prioritization framework for 3,000+ accumulated feature requests, identified 27 broker jobs, validated 8 through 25 user interviews, and used the resulting job map as a live prioritization filter for all incoming channels (Upvoty, CSAT, consulting tickets).
• Responsible for the Scout24 Lighthouse initiative: Document Intelligence with full RAG architecture (semantic chunking, bge-m3 embeddings, pgvector, BM25+Dense hybrid retrieval).
• Reduced lead time of customer feature requests to 3.1 days through code analysis, ticket specification, and independent implementation using a coding agent (Codex).
• Developed an LLM-based support agent (GPT-4o mini, Codex-generated merge requests) that reduced 3rd-level escalations from 40% to 5% of all monthly tickets.
• Integrated six partners through technical coordination, specification, backlog and release management, and led seven full stack developers.
• Eliminated regulatory exposure for brokers in six weeks through risk analysis (BGH ruling on distance selling/GDPR), new audit features, and coordination with legal and data protection officers.

• Spearheaded the integration of a custom Transformer-based encoder into the AFFGANwriting pipeline, replacing the legacy VGG19 architecture to capture richer, high-fidelity writer-style representations.
• Boosted user-study pick-rates by 40%, demonstrating a significant leap in the perceptual quality and realism of the generated handwriting compared to the baseline model.
• Enhanced OCR performance by 20% by implementing a teacher-student framework that leveraged a TrOCR benchmark model for auxiliary training alignment

• Took over and led the operational and IT workstreams to ensure operational readiness on Day 1

• Introduced SMO governance including status meetings and reporting

• Crisis management

• Managed the key ERP and non-ERP workstreams to secure data migration (SAP R3 to S4 Hana) and ensure operational readiness in logistics and production

• Identified actions to address weaknesses/deficits in the existing SMO/IMO structure to meet budget and closing deadline

• Developed and implemented a cut-over strategy including freeze and stock-taking

• Completed the carve-out activities by the closing date, including the separation of the production-specific departments Operations, Logistics, Supply Chain, Sales & Procurement, IT, transfer of all data and documents into the target structure of the acquiring company LDC, and integration of the IT infrastructure into the buyer's target structure

• Reduced the planned 7-day shutdown to 4 days

• Secured operational readiness on Day 1

• Handed over logistics inventory with inventory variance < 1 %

• Technical project management for a new policy and quote management tool in individual, commercial and specialty insurance
• Extending an established standard solution with dedicated lines of business modules for industry and public institutions
• Setting up project structures, teams, organization and communication processes
• Integrating the solution into the existing insurance ecosystem and connecting it to various systems
• Stakeholder management and classical project management (in time, in scope, in budget)
• Overall responsibility for project budget and deliverables
• Initiation, planning, execution, testing and go-live
• Tools used: MS Office, Jira, Confluence, Xray

Software service provider for AI solutions, automation, and custom software.

Team: built from 2 to 10 developers, 8 direct reports, partly remote · Portfolio: 6 parallel projects (€25k–€250k), scaling > €1M

• Ensured delivery capability for 6 parallel customer projects: role model, capacity planning (510–660 productive person-days/year), hiring roadmap with €380k–€440k/year personnel budget
• Established SDLC framework from scratch in under 6 months: REQ/SPEC structure, V-model gates, GitHub Issues as specification, Definition of Done, release process; consistent, auditable development process across all customer projects
• Prepared large program (3,000–4,000 person-days over 18 months) for decision readiness: AI-native industry platform for the construction sector; scoping, team profile for 8–10 developers, phase 0 budget €390k
• Designed and introduced self-hosted AI platform: vLLM, LiteLLM, Qdrant, Supabase; agent architecture, MCP integration, OCR pipelines; prepared GPU investment with break-even model (month 15–16)
• Systematized presales end to end: lead qualification with maturity scoring, discovery workshops, own sizing model, costing with loaded hourly rates, structured handover to development
• Tangibly improved the security level of a customer platform: penetration test incl. re-verification of all findings