Azure OpenAI Service Experts in Germany

• Development of a production-ready Enterprise AI solution for the automated processing of invoices and business documents
• Integration of Azure AI Document Intelligence and LLM technologies into existing business processes
• Development of robust REST APIs for automated document processing and system integration
• Extraction, validation, and storage of structured invoice data in Azure SQL as a base for analytics and machine learning models
• Development of an AI-based recommendation engine with machine learning and deep learning to generate personalized product recommendations based on historical purchase data
• Implementation of logging, monitoring, error handling, and validation mechanisms for stable production use
• Collaboration with business teams to define business rules and integrate the solution into existing enterprise processes

Technologies: Python, Azure AI Document Intelligence, Azure OpenAI, Azure SQL Database, REST APIs, Machine Learning, Deep Learning, OCR, Pandas, JSON, Workflow Automation

• Deployment and scaling of existing ML initiatives, including demand and cash flow forecasts.
• Building robust monitoring with mlflow for data stability, model performance, and drift detection, as well as implementing additional ML use cases.
• Further development of an Agentic AI chatbot for transparent and easy-to-understand model explanations.

• Strategic consulting on AI implementation and innovation for companies in high-end sectors such as fashion, beauty, retail, and hospitality.
• Developing strategic roadmaps and decision support for AI implementation in product-related and creative domains.
• Supporting internal storytelling to foster team and leadership buy-in.
• Structured evaluation of potential AI use cases based on maturity, impact, and technical feasibility.
• Simplifying complex AI concepts, LLM structures, and agentic workflows for decision-makers.
• Applying a clear evaluation model for rapid value realization (Build–Buy–Vibe decision framework).
• Identifying common pitfalls in AI implementation and deriving sustainable deployment patterns.
• Developing curated trend radars and positioning AI within high-end brands and regulated environments.

I designed and developed an AI-powered multi-tenant platform on Azure that transforms SAP process recordings into technical documentation, presentations and automated tests, processing over 15,000 process recordings for enterprise customers like Würth. I owned the architecture, the production releases and the DevOps setup. I also designed a multi-tenant system with SSO and role-based access on Azure. Implemented an MCP Server with Dynamic OAuth Authentication.

Main Tasks:

• Sprint planning and feature preparation
• Design the multi-tenant platform architecture (FastAPI, SQLAlchemy, PostgreSQL row-level security for tenant isolation)
• Develop AI pipelines with Prefect for transcription (Azure Speech API), document generation and SAP screen-recording analysis (Claude, gpt-4-mini)
• Design and implement an MCP server to expose tenant knowledge to LLM clients (Claude), with async retrieval and reranking
• Implement LLM cost tracking, rate limiting and client pooling for Anthropic/OpenAI/Azure OpenAI endpoints
• Set up CI/CD: Docker images to Azure Container Registry, GitHub Actions, Azure Static Web Apps, Alembic migrations in containers
• Manage production releases and execute live data migrations for enterprise customers
• Define engineering standards and architecture patterns for the team

Environment: Azure / Azure Foundry / Python / FastAPI / Prefect / React / PostgreSQL

• Overall responsibility for the project lifecycle from scope definition to completion
• Close collaboration with platform teams, IT leaders, and external service providers
• Application of SAFe principles and structured sprint work
• Creation of a migration roadmap with clear milestones
• Monitoring of the lifecycle: onboarding, repository migration, replication of permissions, and system tests
• Visualization of the architecture with PlantUML and Gliffy as well as documentation in Confluence
• Regular status reports and running knowledge transfer sessions

• ▶ 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.

• Independently managed the POS tender for in-store catering.
• Structured requirements gathering (functional and technical).
• Created a management-ready specification to guide decisions for leadership and IT.
• Market overview of relevant POS providers.
• Close coordination with Galeria's IT and business departments.

Enterprise AI content categorization and AI-powered web research.

• Built multi-LLM evaluation framework with annotated data
• Iterated LLM error rates based on annotated datasets
• Implemented AI-powered web research pipeline Stack: LLM, evals, OpenRouter, Python, Node.js, TypeScript, React

• Acted as technical consultant to optimize multi-layer ensemble models combining ResNet, CNN-BiGRU-Attention, and XGBoost.
• Guided implementation of a Logistic Regression meta-learner to solve class imbalance problems, achieving 92.86% accuracy and 0.9644 AUC on PTB-XL and Chapman-Shaoxing datasets.

• Built a Trend-Scouting AI system to automate technology intelligence in power electronics and semiconductors, combining Azure OpenAI with LangChain, Scrapy-based web crawling for structured, noise-free data acquisition, and automated PDF reporting for internal R&D use. Developed a FastAPI-based (Uvicorn) web application to validate LLM outputs, test prompt strategies, and enable interactive system evaluation.
• Developed a real-time STM32 binary telemetry debugger with a PyQt-based GUI, featuring header-based frame synchronization, anomaly detection, template-driven payload decoding, time-aligned buffering, and live signal visualization.
• Developed an AI-driven power inductor designer using surrogate regression models for accurate electromagnetic and thermal prediction. Integrated multi-objective NSGA-II optimization to generate efficient, manufacturable designs.

• Lecturer for the GenAI Track at the Master School Institute of Technology
• Development of a full-stack AI application (React + Python/FastAPI) for automated supplier product import with intelligent column and category classification (4-layer hierarchical) including human-in-the-loop validation

End-to-end responsibility for all products - concept, architecture, development, and production operation as the sole developer; in addition, customer meetings, proposals, and marketing.

Underwriting Copilot - AI assistant for industrial insurance (in production at customer sites)

• Supports underwriters in analyzing industrial insurance submissions - in production use at an industrial insurer.
• Framework-independent RAG architecture with Hybrid Search (BM25 + pgvector) across large, mixed document sets.
• Two-stage evaluation and observability pipeline (code assertions + LLM-as-Judge) that makes answer quality, retrieval accuracy, and citation integrity measurable in a regression-safe way.

Kaiki Menu Analyzer - Data intelligence platform (in production at customer sites)

• Automatically captures and analyzes menu data from around 25,000 German restaurants.
• Scalable 7-container architecture (FastAPI, partitioned PostgreSQL, Redis/RQ) with LLM-supported extraction of structured data from PDF, HTML, and images.
• Full CI/CD pipelines (GitHub Actions), production cloud deployment, interactive dashboards (Dash).

Kaiki GEO Atlas - GEO platform (in production at customer sites)

• Measures brand visibility across five AI engines (ChatGPT, Gemini, Perplexity, Grok, Claude), each augmented with web search, orchestrated as a DAG workflow pipeline (Dispatcher → Sub-workflows → Scoring → Report) with fail isolation.
• 6-container deployment (FastAPI, Celery, Redis, PostgreSQL); LLM cost estimation, PDF audit report, rule-based cross-signal insights (no extra LLM cost).

Data Pipeline & Analytics Platform - competitive analysis in the automotive aftermarket

• Automated data pipeline with gap analysis algorithms and role-based access control; 230+ tests.
• Backend with FastAPI, PostgreSQL, SQLAlchemy.

Product development (actively in progress)

BankingGPT - AI assistant for complaint management in cooperative banking

• Security architecture at the core: no AI draft reaches the customer without human approval - the approval decision is in auditable code, not in the language model (monotonic: the model may escalate, never downgrade).
• Real agentic building blocks, each with its own boundary: the model chooses tools itself through an MCP server (read-only, allowlist, capped, fail-safe); sensitive cases are handed off via an open A2A protocol (JSON-RPC, Agent Card, message/send/tasks/get; client implemented by me) to a separate specialist agent (securities/law), which never lowers the review requirement (pinned by test).
• Evaluation-driven over ten analysis rounds; uncovered a security flaw through independent review and blind tests that nine automated runs had missed.
• Voice AI frontend, responding live: covered cases are answered in the conversation, sensitive ones escalate before generation; response latency < 7 s measured (local GPU STT/TTS).

Stack & production readiness: Python, pydantic-ai, FastAPI/Celery, PostgreSQL/pgvector, FastMCP, fasta2a, Docker; multi-tenant capable (physical vector isolation per tenant), PII encrypted, OWASP-LLM reviewed, 275 tests, CI/CD; vendor-portable (Ollama / EU Cloud Vertex).

After-Sales Assistant - agentic RAG/GraphRAG assistant on public OEM manuals (automotive after-sales)

• Genuinely agentic on LangGraph: ReAct agent with four tools and conversation memory - the model decides on its own whether to use the manual (RAG, Chroma), a knowledge graph (GraphRAG, Neo4j/Cypher - decodes warning lights), or a workshop/booking service.
• Human-in-the-Loop before the irreversible action: before every appointment booking, the graph pauses (interrupt) and gets the driver's explicit confirmation - the same approval-before-action discipline as in BankingGPT, in a different framework.
• Eval as CI gate: a three-part scorecard (RAGAS grounding + deterministic tool-routing accuracy + DeepEval safety: does the answer mention the warning first when there is a critical warning?) blocks the pipeline; provider-agnostic (OpenAI/Azure/Anthropic), FastAPI with token streaming.

Stack: Python, LangChain/LangGraph, Chroma, Neo4j, RAGAS/DeepEval, FastAPI, Docker.

• Architected and deployed a production-scale GraphRAG system using Neo4j, embeddings, and multi-hop reasoning over 120M+ nodes, improving answer precision by 32%, reducing hallucinations by 41%, and lowering retrieval latency by 38%.
• Designed and implemented an enterprise agent ecosystem using Model Context Protocol (MCP), exposing internal APIs, databases, and services as secure callable tools for autonomous workflows and system integration.
• Designed and deployed a production LLM-based email routing agent using Microsoft Graph API, MCP, and Azure OpenAI, achieving 96% routing accuracy, reducing manual triage workload by 65%, and decreasing response times from 18 hours to under 4 hours.
• Implemented autonomous agent self-correction pipelines using iterative feedback loops (Ralph Wiggum), enabling reliable error detection, automated remediation, and production-safe execution.
• Developed a multimodal semantic search platform using multimodal LLMs and vector embeddings, enabling semantic discovery across 250k+ image and video assets and improving search recall by 48%.

• Project environment: Python, Java, Azure AI Studio & OpenAI Studio, embedding models, LLM as a judge
• Project language: German
• Project role(s): Project manager
• Project management for improving the performance of a chatbot
• Research and evaluation of approaches to improve and measure response accuracy and improve the chatbot's understanding of context
• Coordination of architecture decisions with the technical team and architects
• Coordination and transfer of research results into development tasks