Artificial Neural Network Experts in Germany

• 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.

• 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.

• Idea, design and initial implementation of a service that aggregates publicly available data to estimate prices for certain types of objects
• Collection of data from different data sources and its normalization. Embedding the data using SentenceTransformer and training gradient boost models
• Implementation of a web service that
• reads arbitrary user text
• extends it if some parts of data are missing
• uses a local LLM model to prepare the data for prediction
• embed the data and call for prediction from the gradient boost model
• uses a LLM model to generate a report for the user request including explanations
• Stack: BigQuery, Vertex AI, Cloud Run (GCP), Python, Terraform, DBT, SentenceTransformer, Qwen
• Minor SEO optimizations
• More to come...

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.

• Spearheaded the development and deployment of a Generative AI solution tailored for the automotive industry focusing on improving customer experience through AI-driven innovations.

• Conducted in-depth market research to understand unique challenges and opportunities within the automotive sector by analyzing industry trends, customer pain points, and competitive offerings to inform the product strategy.

• Formulated a strategic vision for the Generative AI solution targeting personalized customer experiences, aligned product vision with the company’s long-term goals and automotive market demands.

• Enhanced customer satisfaction by introducing personalized AI-driven features, achieving a 15% increase in customer engagement and loyalty.

• Attended and represented Audi AG on a group-wide level in workshops for AI strategy for customer experience.

• Leveraged knowledge of recurrent neural networks and transformer architecture.

• Utilized GPT-3 generative AI frameworks.

• Employed TensorFlow and PyTorch for machine learning.

• Used Tableau from Salesforce for data analysis and visualization.

• Served as solution manager for the Business Architecture team.

• Collaborated with business stakeholders within Audi OEM to gather requirements for CRM strategy including marketing department, CRM heads across countries, VW group brands and CARIAD SE.

• Represented Audi AG in CRM strategy workshops held in different countries.

• Discussed CRM strategy with head of CRM and Data based on workshop outcomes.

• Conducted business analysis on gathered market data to improve customer experience.

• Planned and launched marketing campaigns such as welcome mailing, license renewal reminders, Audi Progress Circle and Black Friday campaigns.

• Managed project budget.

• Acted as solution manager for the ONE.CRM team at CARIAD SE on loan from Audi AG.

• Collaborated with business owners of VW group brands to develop a central solution.

• Represented CARIAD SE in CRM strategy workshops in Spain, France and Italy.

• Discussed CRM strategy with head of CRM at CARIAD SE based on workshop outcomes.

• Conducted business analysis on market and brand data to improve customer experience.

• Planned and delivered campaign capabilities from template to brands such as welcome mailing for Audi AG, SEAT and SKODA.

• Managed project budget together with head of CRM.