Vector Database Experts in Munich

• Created a multi-agentic system supported by a knowledge graph to automate drafting of research papers
• Used multiple experts (OpenAI models) collaborating during document drafting
• Extracted useful information from the knowledge graph
• Technologies: LangChain, LangGraph, Smolagents, LlamaIndex, dspy
• Infrastructure: Terraform and GitHub Actions (CI/CD) on AWS
• Deployed initial application as a Streamlit app

• 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).

AI-driven automation of purchasing on a printing company's website, including selecting delivery times, order options, ordering, payment, and uploading print data from the Lumiz Cloud.

• Integrated LangChain middleware between AEM and SAP PIM system
• Developed a FastAPI interface for system communication
• Implemented vector embeddings for semantic product search
• Evaluated LLM models (Vertex AI/Gemini, LM Studio, Hugging Face, OpenAI) for product analysis
• Developed an AEM component to display product recommendations and integrated the recommendation API into the AEM authoring process
• Designed and implemented Pinecone vector database for product embeddings
• Optimized response times and caching strategies
• Evaluated Vertex AI Studio for LLM testing and prompt workflows
• Implemented secure API routing and access control for AI components via FastAPI and gateway validation

• Completed an intensive AI Engineering Program focused on LLM evaluation, retrieval, agent orchestration, and multimodal workflows.
• Designed retrieval pipelines with document ingestion, semantic search, and citation-aware outputs using LangChain and ChromaDB.
• Built LangGraph-based agent workflows with state handling, clarification loops, and human-in-the-loop approval steps.
• Applied prompt engineering and evaluation patterns, including scoring logic and guardrails, to improve output quality and reliability.
• Worked extensively with Python, FastAPI, OpenAI APIs, LangChain, LangGraph, and ChromaDB in end-to-end implementations.

• Architected and built a GenAI-based automated asset-generation tool for social media campaigns using Nano Banana and Python. It takes a campaign brief, target audience, and two products as input, generates optimized prompts for image and text creation, and uses functions for text positioning, visually appealing overlays, resizing, and structured uploads to AWS S3.
• Engineered and built a multi-agent news intelligence platform with specialized roles including retriever agents (Tavily web scraping), synthesizer agents, and Claude as curator/orchestrator, designing autonomous agent collaboration patterns using LangChain and RAG.
• Built an autonomous customer service agent using n8n and LLMs, delivering end-to-end support automation with transparent reasoning, governance controls, and scalable workflow orchestration using Python and vector databases.
• Developed a financial validation engine featuring ML-powered anomaly detection for invoice plausibility, compliance automation, and risk mitigation using TensorFlow and SQL.
• Created a cost optimization application using OCR, AI, Pandas, and NumPy for data analysis to identify cost optimization potential.

• Co-founded an AI venture focused on building production-grade LLM applications and agentic systems
• Designed and implemented multi-agent AI workflows for financial and trading applications
• Developed LLM-powered copilot architectures for portfolio analysis, trade management, and personalized user coaching
• Built on-device and edge-deployed inference applications, optimizing models for low latency, privacy, and resource-constrained environments
• Led system architecture decisions across model selection, orchestration, state management, and deployment

• Research and develop models for chatbots, NLP and LLMs (e.g. Llama, Qwen, OpenAI)
• Enhance chatbots with RAG, in-context learning
• Supervised fine-tuning (PEFT, LoRA), Huggingface or Unsloth
• Advanced training methods: Test-time training, (transductive) active learning, reinforcement learning
• High-throughput serving with vLLM
• Apply embedding models (e.g. SentenceTransformers), similarity/vector search or vector DB or ranking (e.g. LlamaIndex, Faiss, LangChain)
• Generate and filter synthetic data, clustering
• Detect hallucinations
• Evaluate chatbot models (Rouge, BLEU, F1-Score, Recall, Precision)
• Visualization of experiments (matplotlib)

• Architected and implemented an enterprise-grade AI Agent Platform leveraging Retrieval Augmented Generation (RAG) architecture to enhance clinical data insights.
• Established robust CI/CD pipelines for LLM applications using CDK and Jenkins, significantly reducing deployment times.
• Implemented comprehensive observability solutions that increased agent reliability across pharmaceutical environments.
• Designed scalable AI workflows with advanced orchestration that optimized context handling for enterprise data sources.
• Technologies: AI Agents (LangChain, LangGraph, Bedrock, Smolagents, Streamlit); LLM Operations (Tracing, Testing, Evaluation, LangSmith, LangFuse); Infrastructure-As-Code (AWS CDK, Terraform, Typescript, Jenkins); Vectors, Embeddings, RAG (OpenSearch, pgvector, PDF Extraction)

• Conducted stakeholder interviews and market analysis to identify challenges in secure genetic data use, translating insights into a product concept and AI graph-RAG prototype.

• Head of technical overall integration NSC (National Secure Cloud project with about 60 employees).

• Technical integration of all subprojects into one product, definition of interfaces, basic components of a cloud including hardware, technical architecture of the IABG base.

• Development of a Cloud Management Platform (CMP) that can create a private/mixed cloud of any complexity based on a textual description with one click or interactively.

• CMP also includes the complete hardware management cycle.

• As a foundation, it uses Kubernetes, OpenStack, and Hadoop.

• The management layer includes Harbor, Gitea, Longhorn, Keycloak, Rancher and Jenkins, which are automatically configured.

• The private cloud can run any customer workloads, including a full Hadoop stack with HDFS, Spark, MapReduce, Mesos, HBase and around 20 other ML/DL technologies.

• Hadoop worker clusters can also be automatically installed on bare metal or commodity hardware without Kubernetes.

• OpenStack with Nova, Neutron, Ironic, Swift, Cinder, Ceph.

• Development of a Java application Rudi: SOAP, REST, containers, database.

• Technologies: Kubernetes (K3s, RKE2, Minikube, Harbor, Gitea, Jenkins, Longhorn, Keycloak, Rancher), OpenStack (Nova, Neutron, Keystone, Swift, Ceph, Cinder, Sahara, Magnum, Kayobe, Kolla, Bigrost, Ironic), Hadoop (HDFS, Ambari, Solr, Livy, Ranger, YARN, Tez, HBase, Kafka, Hive, Zookeeper, MapReduce, Spark, Oozie, Flink), virtualization (Kubernetes (K3s), VMware, Oracle), scripting (Ansible, Puppet, Juju, Shell, Groovy, Gradle, Maven).

• Designed and developed end-to-end web and mobile products as a full-stack engineer, working across Python/FastAPI backends, databases, and React / React Native frontends.
• Built LLM- and agentic-AI systems using LangChain, LangGraph, CrewAI, Langfuse, and vector databases, focusing on reliability, observability, and clean abstractions.
• Developed a text-to-SQL assistant for the marketing team that lets non-technical users query a large retail-style dataset in natural language, returning clear analytics and campaign insights.
• Helped reduce ad-hoc SQL/reporting requests to engineering by 60% and cut time-to-insight for common marketing queries from hours to minutes.
• Created a full-stack mobile app where Apple Health data is processed and fed into an LLM to generate personalised, VO2-max–based health coaching and insights, owning architecture from frontend to backend and auth.