Artificial Neural Network Experts

• Claude Code subagents, MCP, Pydantic V2, pytest, bandit

• Designed and shipped 3 specialized agents that hand work down a line: a research agent writes a cited implementation spec, a coding agent builds the modular code and its tests, a review agent ranks findings by severity and applies the fixes. Each handoff is a structured document, so no stage depends on another agent's context window.

• Connected the research agent to an academic-research MCP server (Semantic Scholar, ArXiv, Hugging Face Hub, citation snowballing) so every reference traces to a tool result rather than the model. Gated commits behind ruff, mypy, pytest and bandit, required human sign-off before installs and commits, and persisted session state on disk so long runs survive a context reset.

Managing Director | Omnia Kassel UG

Corporate management, international business development, technology and innovation management

• Corporate management and international business development: Strategic and operational management of a technology-oriented consulting company. International B2B business development, development of new business areas, and establishment and maintenance of industrial, technology, and procurement partnerships.

• Technology and innovation management: Identification and evaluation of new technologies with regard to technical feasibility, commercial potential, and practical applications. Development of innovative business models, technology transfer, and support for demanding innovation projects.

• Development and project management: Design, planning, and management of technical development, procurement, and customer projects. Technical specifications, international supplier selection, coordination of external development partners, and evaluation and implementation of customer-specific solutions.

• AI research, systems development, and technology evaluation: Early recognition of the fundamental technological change brought about by generative AI. For around four years, self-initiated, almost daily intensive research, development, and testing work with leading language models, multimodal AI systems, and different model generations. Independent design and testing of around 200 complex AI workflows, multi-agent methods, and book, proposal, and evaluation agents.

• AI-supported customer projects and multimodal production: Practical implementation of proprietary and confidential customer assignments in technical design, project development, proposal preparation, specialist texts, and comprehensive documentation. Development and production of texts, images, animations, videos, speech, and avatar applications. A total of around 750 productive work results from various AI-supported projects.

• AI quality assurance, process development, and efficiency improvement: Development of multi-stage, cross-model testing and correction procedures with source comparison, independent review, and systematic error analysis. In own task-specific comparative measurements, reduced selected processing times from eight hours to one hour and improved measured accuracy from about 95 % to up to 99 %. Transfer of the findings into productive work processes and commercially usable customer solutions.

Project-based activity and availability: The entrepreneurial activities are organized on a project basis and are not connected with permanent full-time operational utilization. Therefore, there is substantial time available for external consulting, development, and management assignments, including projects with a high workload.

• 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

Statistical Forecasting Algorithm

• Improvement of an statistical probabilistic forecasting algorithm for sales + evaluation
• Migration from R/On-premise to Python/Snowflake
• Productionalization on Snowflake in cooperation with data engineers & DevOps

Monitoring Dashboard

• Data engineering for preparation & provisioning of necessary data/resources on Snowflake
• Development & deployment of a Streamlit dashboard in Snowflake

ML-based Probabilistic Forecasting on Vertex AI

• Development of a ML-based probabilistic forecasting algorithm from scratch
• Implementation of MLOps pipeline in Kubeflow on Google Cloud Vertex AI

Tech Stack: Python, Snowflake/Snowpark, R, Streamlit, Gitlab/Gitlab CICD, Terraform, Google Cloud, Vertex AI (aiplatform SDK, gcloud CLI, feature store, model registry, etc), kubeflow

• Building, implementing and selling automated Data Science solutions such as Scorecard Factory and Forecast Factory
• Implementation of automated end-to-end cloud processes
• Development of LLM and NLP models
• Creation of interactive reports
• Support for national and international large corporations as well as medium-sized companies in implementing ML projects

• Delivered MVP-focused full-stack architecture for a health-sector client: Vite/React frontend, backend services on Google Cloud Run, and Supabase for database plus IAM/authentication.
• Supported product requirements engineering and prioritized cost-aware workload placement, implementing browser-side/edge computation where feasible before moving logic to backend services.

• Designed and deployed enterprise Retrieval-Augmented Generation (RAG) applications using LangChain, LangGraph, vector databases, embeddings, and open-source LLMs served through vLLM on GCP GPU infrastructure.
• Built agentic AI workflows using LangGraph with planning, reasoning, tool execution, persistent memory, session management, and Human-in-the-Loop approval mechanisms.
• Developed LLM-powered automation systems integrating BigQuery, SQL pipelines, and external advertising APIs including Meta, TikTok, Amazon, Snapchat, Google, and Pinterest, reducing manual operational workflows.
• Architected multi-agent AI systems for enterprise analytics and decision-support workflows, enabling autonomous task execution and intelligent data interactions.
• Implemented retrieval optimization strategies including multi-retriever architectures, semantic search, context optimization, and query improvement techniques, improving response relevance by approximately 40%.
• Engineered structured prompting strategies, function-calling schemas, and validation workflows to improve reliability of multi-step LLM applications.
• Designed scalable AI services using Python, FastAPI, Cloud Run, Pub/Sub, BigQuery, Docker, and cloud-native deployment architectures.

• It is like a startup within REWE, where we have to build a new forecasting system on Google Cloud Platform from the scratch. Although, officially my role is called MLOps, my actual tasks also include development of data processing pipelines (data engineering) and data scientists tasks such as feature engineering and model trainings.
• GCP: Terraform (tofu), Vertex AI (Kubeflow), Cloud Run, IAM, Google Cloud Storage, BigQuery, Artifact Registry
• Data engineering: Snowflake as the main data warehouse, Terraform, DBT for data model implementations
• CI/CD: GitLab. We have built a CI/CD pipeline that automates deployments of new releases up to production environment
• Development of feature store and data synchronization between environments
• Data science: evaluation of different forecasting models, including CatBoost, Contextual Gamma and Random Forest; implementation of training pipelines using Kubeflow on Vertex AI; scaling and development of an event-driven interface using Kafka as a forecasting service; evaluation of MLFlow for model tracking and model registry
• Implementation of REST API using KeyCloak OAuth2 and OpenID (JWT)
• Monitoring: implementation of dashboards with Grafana, Prometheus, Mimir, Streamlit and Loki to monitor prediction metrics, GCP and Snowflake costs for pipelines, and system metrics
• Development of Copilot Agent Skills

• Developed a CNN-based pedestrian detection system using LiDAR data
• Created Python scripts for bounding boxes, dataset labeling, and data conversion
• Evaluated model performance on datasets with point clouds

Development of AI-based and classical models for analyzing medical and patient data, including medication analyses, diagnosis analyses, forecasts, procedure analyses, dosage analyses, comorbidity analyses, prescription analyses, patient potential analyses, and referral profile analyses. Analyses in the area of Real World Evidence.

• Gathering customer requirements
• Planning the subproject
• Designing and defining KPIs
• Designing and developing models and visualizations of the results using customer dashboards
• Developing and implementing DWH adjustments
• Deriving recommendations for action

Methods, technologies: Simulation, Artificial Intelligence, Python, R, SQL, Microsoft Power BI, Amazon Web Services, Elasticsearch, PostgreSQL, Databricks, Multivariate Statistics

• Strategic consulting, technical consulting, interim management, and training
• Management consulting and development of application solutions through interdisciplinary solution approaches
• Employee and team development as well as innovation and communication management

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.

• Crypto quant strategy development, automated trade execution, onchain data client (Ethereum / Solana)
• Data and trade architecture development for liquidity provision

I help leadership teams turn the potential of AI into measurable business results — fast, pragmatic, and with people at the core.

As Co-Founder of Infinite Mind, I work with CEOs and innovation leaders to identify high-impact AI opportunities, design actionable solutions, and support adoption across the organization. Our focus: driving productivity gains, smarter workflows, and scalable value.

Over the past ten years, I've worked at the intersection of Digital Transformation, Data, and Machine Learning, advising companies in software, high-tech, media, and insurance. I’ve led large-scale initiatives, including the group-wide adoption of Generative AI, and understand the strategic and human challenges of driving change at scale.

I combine a technical background in machine learning (M.Sc. Electrical & Computer Engineering, TUM) with a broader perspective shaped by degrees in Physics and Philosophy (LMU Munich). In addition to my consulting work, I’ve co-founded a tech-enabled charity and supported early-stage founders as a business coach.

If you're looking to go beyond the AI hype and make it actually work in your business — let’s talk.