Multi-Agent Systems Experts in Germany

• Task Engineering: Evaluating Coding Agents.
• Asset Creation: Building realistic task environments using datasets and files in German. Crucially, these assets must remain in the target language to genuinely measure multilingual handling.
• Prompting & Translation: finding failure points where AI does not work, in German.
• Implementation & Verification: Supporting the development of robust solutions (reference implementations) and write highly reliable, deterministic verifier scripts (using rubric-based judging only when strictly necessary).
• Calibration & Execution: Analyze execution logs and calibrate task difficulty (Easy to Very Hard) using standard Terminal-Bench run configurations against various model tiers (Haiku, Opus).
• Quality Assurance: Participation in a rigorous, 4-layer human quality control process (creation, human review, calibration review, and audit) alongside automated LLM-based checks to ensure fairness, grammatical accuracy, and benchmark integrity.
• Linguistic Review: Reviewing AI benchmark tasks across Hindi, Arabic, Japanese, Chinese, Czech and Turkish.

With project PRIZMA, DB will modernize its infrastructure on the one hand, and develop a fail-safe IT landscape on the other hand, which can be restored quickly and securely in case of a disaster.

• Capture current architectures of existing systems as well as methodical consulting and development of target architectures
• Deepen and maintain the building plan / target IT landscape
• Implement technical architecture concepts & architecture descriptions
• Implement migration concepts for updating and further developing the platform and information systems
• Assess submitted improvement suggestions as part of the project
• Capability management: identify capability gaps, develop target visions, and support transformation planning within the enterprise architecture.
• Create a compatibility matrix of the components in use and compare dependencies of specific versions
• Create an IT concept for extending the platform with the following topics: hardware and software requirements, security, licensing, high availability, load balancing, backup & recovery, update strategy, monitoring integration, etc.
• Coordinate with business architects as well as technical architects from the cross-functional architecture area of the PRISMA program for the topics (backup, Active Directory, monitoring, Citrix, and business applications ...)
• Status meetings and alignment of project planning with the Release Train Engineer / Project Manager
• Advise the Release Train Engineer / Project Manager in identifying project risks
• Advise the System Architect Engineers in steering the implementation of the concept
• Implement the IT concept
• Document the infrastructure

Label: MS Project, LINUX, Windows, ORACLE, Java, REST, SharePoint, Microsoft Exchange, UML, Enterprise Architect, BPMN, AZURE, AWS, V-MODEL, Micro Service, VisualStudio, SAP S/4HANA, SCRUM(SAFE), ESB (TIBCO), Python, Innovator, LeanIX (TOGAF), Ansible, Ansible Tower, Ansible Automation, ROBOT, SpringBoot

Scope: Embedded as FP&A Data & AI Architect within the Finance function of a major European refrigeration manufacturer, leading the transformation of manual, fragmented financial reporting into an automated, governance-driven intelligence platform. Driving the shift from Excel-based controlling to structured data architecture, Power BI analytics, and AI-assisted financial operations.

Financial Data Integrity & ERP Governance

• Initiated and led GL vs. subledger reconciliation investigations, identifying and resolving structural mismatches between General Ledger and subledger data that had gone undetected prior to engagement
• Conducted asset analysis to identify items missing from General Ledger postings, surfacing gaps in fixed asset tracking and period-end completeness
• Validated SAP reports, establishing baseline data quality standards for Finance team consumption
• Established systematic SAP data validation framework ensuring ongoing integrity between ERP postings and downstream reporting outputs

Finance Reporting Transformation

• Designed and implemented a structured Transformation Project approach for converting manual Finance reports into fully automated processes
• Created and owns the Data Reporting Audit Log; a centralized tracking system capturing report owners, stakeholders, data sources, manual effort estimates, and automation opportunity scores across the Finance function
• Mapped the full reporting landscape identifying quick-win automation targets and strategic Power BI migration candidates
• Actively reducing manual Excel and PowerPoint dependency across FP&A workflows; replacing point-in-time snapshots with live, governed data models

Power BI & Analytics Enablement

• Introduced and presented Power BI as the strategic reporting platform to Finance leadership, building internal buy-in for the BI transformation roadmap
• Designed initial Power BI architecture aligned with SAP, Salesforce and Oracle data structures and FP&A reporting requirements
• Established report ownership, governance documentation, and data lineage standards enabling sustainable self-service analytics across the Finance team

Transformation Infrastructure & Collaboration

• Configured and deployed Jira as the transformation project management hub, establishing structured sprint workflows, backlog management, and progress visibility for Finance IT initiatives
• Proposed and initiated a dedicated FP&A Communication & Transformation Hub, a structured cross-functional forum aligning Finance, IT, and business stakeholders around the reporting transformation roadmap
• Positioned the Finance function as an active driver of data governance and digital transformation within the broader organization

Outcomes

• GL/subledger reconciliation gaps identified and investigation framework established within first two weeks of engagement
• Data Reporting Audit Log deployed; first structured inventory of Finance reporting landscape in company history
• Power BI transformation roadmap presented and approved by Finance leadership
• Jira-based project governance live; Finance transformation now tracked with full sprint visibility

Technologies: SAP FI/CO · Power BI · DAX · SQL · Excel (advanced) · Power Query (M) · Power Automate · VBA · Jira · Microsoft 365 · SharePoint · Salesforce (Sales Data) · Oracle HCM · Python

agentic-engineer.online is my publicly testable live demo and at the same time the platform where I show my work. Originally created as a recruitment trial task, I have since continued to run it as my own demo, learning, and product project — on a Hetzner VPS behind a Cloudflare tunnel, through a multi-stage AI-orchestrated deploy pipeline with snapshot rollback. If a deploy step breaks, the system falls back to the last clean snapshot, the script is adjusted, the test repeated — empirical, test-driven, without hand tuning.

• Technically behind it: Python and FastAPI, an OpenRouter model cascade, SQLite persistence, and Cloudflare edge tuning.
• I am the developer and the strictest customer of my own AI work in one person — what started as a prototype has become a tool I use every day and against which I test my own products.

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.

• ▶ Built real-time voice assistant (STT → LLM → TTS pipeline) benchmarking and evaluating multiple STT providers including faster-whisper and Azure Speech. achieved sub-3s latency, Groq API (Llama 3) with multi-turn memory - directly handling edge cases in dictation, names and passcode recognition.

Re-platforming an e-commerce shop to a microservice architecture

• Goal: Replace an outdated Shopware system with a scalable, future-proof solution based on microservices and a headless architecture.
• Led a full architecture consulting process and defined the microservice boundaries based on a headless architecture with commercetools as PIM/OMS and Next.js as the frontend solution.
• Developed and integrated several decentralized services (e.g. internationalization, personalization).
• Took over the configuration of central third-party systems such as Contentstack and Algolia.
• Built a stable cloud infrastructure on Google Cloud with monitoring via Grafana.

Technologies: commercetools, Next.js, Contentstack, Algolia, Google Cloud, Grafana, TypeScript, Shopware

Development of an international e-commerce platform

• Goal: Build a high-performance, user-friendly and international e-commerce platform.
• Defined a scalable, high-performance and maintainable software architecture that served as the foundation for the platform's international expansion.
• Selected a best-of-breed technology stack that enabled the development of an industry-leading shop and reduced development effort for new features by 30%.
• Ensured seamless integration of critical third-party systems (PIM, CRM, ERP) to guarantee end-to-end business processes and a consistent data foundation.
• Implemented comprehensive tracking and analytics tools for continuous performance monitoring and optimization of the customer journey.

Technologies: React.js, Next.js, commerceTools, Algolia, Salesforce, Heroku, CI/CD, PHP, Google Analytics

AI-powered personalization and customer data platform in e-commerce

• Goal: Replace static content with a dynamic, AI-based personalization strategy to increase user relevance and automate marketing processes.
• Designed and built a customer data platform to aggregate and combine customer and analytics data from distributed sources.
• Implemented automated categorization of customer profiles as the basis for delivering personalized content and product recommendations in the Shopware frontend.
• Developed a semantic similarity algorithm based on Python and OpenAI to calculate product and content similarity from user profiles.
• Built the technical connection to retail media platforms to control external ad placements along the customer journey.

Technologies: Shopware 6, Python 3, OpenAI, Elasticsearch, PHP, Symfony, Twig

Shopware tracking & consent architecture (GDPR) for 4 online shops

• Goal: Build a unified, GDPR-compliant tracking infrastructure across multiple shops with central consent management across several Shopware instances.
• Defined a comprehensive tracking guide and developed a modular architecture compatible across multiple Shopware versions.
• GDPR-compliant integration of Usercentrics and Adobe Launch through a central tag manager.
• Full tracking setup (page, order, product, user) incl. partner-specific tracking (Emarsys, Channelpilot, etc.).
• Detailed event and error tracking to proactively identify technical drop-offs.

Technologies: Shopware, Adobe Analytics, Usercentrics, Tag Manager, PHP, MySQL, GDPR

AI/LLM search engine with RAG and hybrid search (Python, Elasticsearch)

• Goal: Build an AI-powered search engine with RAG architecture and hybrid search to accurately match service providers from over 500,000 company records.
• Developed an automated data pipeline (web scraping + LLM) that continuously crawls company data and converts it into structured formats using LLMs.
• Implemented a RAG workflow incl. vectorization for semantic search to increase search accuracy and relevance.
• Configured and fine-tuned Elasticsearch for hybrid search (vector + keyword search).
• End-to-end development of backend API, frontend and deployment on live servers.

Technologies: Python, FastAPI, Elasticsearch, LLM, RAG, React, Docker, Web Scraping

AI/computer vision system (Python, ML) – object detection under difficult conditions

• Goal: Develop an AI-powered recognition system with reliable performance even in rain, fog, snow and darkness.
• Built and annotated a large training dataset incl. difficult conditions.
• Trained a YOLO-based object detection model; carried out systematic error analysis and improved data quality and preprocessing.
• Coordinated with stakeholders through regular status updates.

Technologies: Python, Machine Learning, TensorFlow, PyTorch, YOLO, OpenCV

• Responsible for concept, camera, editing, animation, and grading for corporate and B2B productions
• Managing projects from budgeting to shoot and post-production through to delivery
• Since 2023, consistently using an AI-based production pipeline: Runway, Kling, Veo, Sora, and Seedance for stills and moving image
• ComfyUI for character consistency, ElevenLabs for voice, HeyGen for avatars
• Building reproducible workflows for scalable social formats
• Building local LLM infrastructure on my own GPU hardware: Ollama, multi-agent systems, RAG, speech-to-text, and text-to-speech
• Process automation for lead generation, email and API workflows, reporting, and document creation

• Enterprise-grade multi-agent AI orchestration platform built with Go and Kubernetes for scalable, secure agent coordination in cloud-native environments.
• Multi-agent orchestration with intelligent workload distribution and dynamic scaling.
• Cloud-native architecture with Kubernetes deployment and horizontal auto-scaling.
• Real-time coordination with sub-100ms agent communication using Go channels.
• Enterprise security with zero-trust architecture, RBAC, and comprehensive audit trails.
• Visual workflow engine with monitoring, observability, and API gateway integration.
• Technologies: Go, Kubernetes, ArangoDB, gRPC, Prometheus, Grafana.

• Codebase Evaluation & Problem Design: Designed and stress-tested complex software engineering problems against large open-source Python codebases (including pandas), requiring deep context acquisition and architectural understanding to produce well-scoped, realistic problem statements aligned to strict correctness guidelines.
• Agent Failure Analysis: Assessed LLM coding agent solutions for correctness and completeness, identifying meaningful failures across edge case handling, dtype behaviour, and multi-column NaN propagation logic; documented findings with precision for downstream evaluation use.
• Programmatic Test Suite Development: Authored comprehensive pytest suites to programmatically verify agent-generated solutions against defined requirements, with deliberate coverage of boundary conditions and failure modes not caught by naive implementations.
• Containerised Environment Engineering: Built and debugged Docker environments for reproducible agent execution, including git-based repository provisioning, dependency pinning with npm ci, and multi-stage Dockerfile authoring across Linux-based containers.

• Built a custom AI chatbot for an e-commerce client using GPT-4 and LangChain with RAG, reducing customer support ticket volume by 45% and improving response accuracy to 92%.
• Designed and deployed an intelligent document processing system using LlamaIndex, Pinecone, and FastAPI for a FinTech startup, enabling semantic search across 100K+ financial documents.
• Developed multi-agent AI workflows using CrewAI and LangGraph for a marketing agency, automating lead research, content generation, and outreach — saving 20+ hours/week of manual work.
• Created AI-powered automation pipelines using n8n, Make, and Zapier integrated with CRMs (GoHighLevel, HubSpot), reducing manual data entry by 80% for a real estate firm.
• Delivered prompt engineering and LLM fine-tuning consulting for multiple clients, optimizing AI model outputs for customer support, content creation, and data extraction use cases.
• Built production-ready REST APIs with Python and FastAPI to serve AI models on AWS and GCP, handling 10K+ daily requests with 99.9% uptime.

• Governed multi-agent orchestration for regulated, EU-based companies – self-hostable, compliant with the EU AI Act and GDPR („by design“), BYOM (own models/GPU).
• Two-gate governance: agent deliberation + mandatory human approval, full signed audit trail; graduated autonomy model („internal → autonomous per skill“).
• Verified knowledge graph („Company Brain“) with source evidence for every answer; own orchestration framework (Virtual Team Framework).
• Industry solutions for financial services: compliance monitoring, invoice and contract review; hands-on development with LLMs (including Anthropic/Claude), agentic workflows, RAG.
• Building the governance-focused multi-agent platform TeamIntel (see AI reference projects).

Overall architecture and technical implementation of a Wix-based subscription frontend with Stripe payments and connection to Axxessio's SaaS backend. Implemented Stripe Checkout, subscriptions, webhooks, and transaction logging end to end. Customer data and contract information transferred automatically via a JWT-protected REST API. Designed and documented proxy and security architecture for IP whitelisting, HMAC, and operations, and aligned it with the backend team.

Stack: Wix Studio, Wix Velo, JavaScript, Stripe, Webhooks, JWT, HMAC, REST API, Hetzner, Cloudflare

OpsWorker turns Kubernetes alerts into root-cause analyses, on top of the monitoring a team already runs. I lead the technical side: the agent architecture, the AWS infrastructure it runs on (fully inside EU regions), and the engineering decisions behind it, read-only in the cluster by default, human in the loop for judgment. The stack underneath: Amazon Bedrock and Bedrock AgentCore, agents built with the Strands Agents SDK, the Claude and OpenAI APIs, and the Kubernetes API.