Google Vertex AI Experts in Germany

Evidence-led health intelligence platform turning published research into personal health protocols. It scores 430 habits, foods, and supplements against the studies behind them, and moves the score when the evidence moves. Built solo.

• Built the daily ingestion pipeline across PubMed, bioRxiv, and medRxiv: 43,000+ papers from 3,400+ journals processed into 230,000+ typed evidence claims, each one traceable back to the study it came from.
• Designed the six-factor evidence scoring model and the public changelog behind it, so no recommendation ever appears without the papers underneath it. 23,000+ grade changes recorded and explained to date.
• Shipped an entity information model connecting every intervention to its mechanisms, biomarkers, and outcomes: 118 biomarkers with region-specific reference ranges, 77 mechanisms, 32 graded outcomes.
• Built the personalisation layer: blood panel ingestion that reads lab PDFs with a vision model and corrects results for draw time against the user's wake anchor, plus Oura, WHOOP, and Withings integration for daily readiness context.
• Operate eleven specialised review agents over the corpus and codebase, covering paper curation, retrieval quality, health-claim compliance across EU and US regimes, and security.
• Shipped the Evidence Assistant, a RAG assistant that answers from the claim database and cites the underlying papers, plus a B2B practitioner tier, an Expo React Native app, and localisation across 3 languages and 7 markets.

Stack: Next.js 16, TypeScript, Supabase, pgvector, Anthropic Claude, Vercel, DeepInfra.

• Development of an AI-powered project organization tool for a civil engineering company that intelligently links project, task, tender, schedule, and document data through a knowledge graph.
• Implementation of AI features for document analysis, information extraction, context-based assistance, and voice-based data capture based on Microsoft Azure AI, reducing administrative effort, making information available faster, and supporting project teams in decision-making.
• Tech stack: Python, React, TypeScript, FastAPI, Claude Code, Codex, Graphify, PostgreSQL, Microsoft Azure AI Foundry, Azure OpenAI, Azure AI Speech, Azure AI Document Intelligence, Microsoft Graph, Microsoft Entra ID, Docker, Git, CI/CD.

• 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

• Own the 12–18 month roadmap and key outcomes for Elli's enterprise customer platform, covering onboarding, pricing, billing, analytics and broader platform modernization; redesigned the Fleet onboarding funnel to double conversion, supporting a projected €20.7M revenue uplift by 2028.
• Lead the broader Energy Intelligence product and directly own its AI/ML, asset and portfolio-optimization capabilities, including MLOps and safe strategy deployment, strategy lifecycle management and backtesting; delegated data and V2G integration roadmap ownership to a new PO as the platform scope expanded.
• Built a Human-in-the-loop GenAI/RAG support workflow, increasing L1 resolution by 24%, routing accuracy to 91%, and reducing L2 workload by 30%.
• Introduced standardized data contracts and a self-service Python toolkit for traders and Data Scientists, increasing platform adoption by 15% and reducing support effort by 50%.
• Built and scaled a real-time orchestration product from 32 to 3,000+ endpoints across four markets, growing recurring revenue from €1.4k to €56.3k MRR.
• Developed product and AI capability across the organization, training 20 PMs on RAG, agents and prototyping; mentoring a junior PM and coaching an Enterprise Platform Tech Lead toward Product Management ownership.

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

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

• 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

• Acquires new B2B customers for an AI SaaS startup in the public tendering space and books product demos with IT decision-makers.
• Qualifies target customers based on a defined ideal customer profile, including discovery, needs analysis, and objection handling.
• Builds domain knowledge in public procurement (EVB-IT, German and EU procurement portals) for conversations on equal footing.

• 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.

• 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.

• 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, complete signed audit trail; graduated autonomy model („internal → autonomous per skill“).
• Verified knowledge graph („Company Brain“) with source evidence for each answer; proprietary 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.
• Development of the governance-focused multi-agent platform TeamIntel (see AI reference projects).

• 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

Conducted an independent technical assessment of an AI-enabled software platform, combining AI risk auditing, cybersecurity analysis and software architecture review. Reviewed application components, APIs, data flows, LLM integrations, retrieval-augmented generation, multi-agent orchestration, authentication, tenant isolation, dependency vulnerabilities, AI governance and model lifecycle controls. Authored a technical audit report with a structured risk register, source-code evidence, regulatory references, corrective actions, AI system inventory, risk classification, remediation roadmap and Key Risk Indicators.

Technologies: TypeScript, JavaScript, React, Next.js, Node.js, REST APIs, MongoDB, Redis, AWS serverless services, OAuth 2.0 / OpenID Connect, LLM APIs, RAG, vector search, multi-agent orchestration, Model Context Protocol, C4 architecture modelling, threat modelling, NIST AI RMF, ISO/IEC 42001, ISO/IEC 23894, OWASP guidance, MITRE ATLAS

End-to-end responsibility for all products – conception, architecture, development, and production operations as the sole developer; also customer discussions, proposals, and marketing.

Underwriting Copilot – AI assistant for industrial insurance (in production with a customer)

• Supports underwriters in analyzing industrial insurance submissions – in production at an industrial insurer.
• Framework-independent RAG architecture with Hybrid Search (BM25 + pgvector) across large, heterogeneous document collections.
• 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 with a customer)

• Automatically collects and analyzes food 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.
• Complete CI/CD pipelines (GitHub Actions), production cloud deployment, interactive dashboards (Dash).

Kaiki GEO Atlas – GEO platform (in production with a customer)

• 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 additional LLM effort).

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 development)

BankingGPT – AI assistant for complaint management in cooperative banking

• Security architecture at its core: no AI draft reaches the customer without human approval – the approval decision is stored in auditable code, not in the language model (monotonic: the model may increase the level, but never lower it).
• Genuine agentic components, each with its own boundaries: the model selects tools itself through an MCP server (read-only, allowlisted, capped, fail-safe); sensitive cases are sent via the open A2A protocol (JSON-RPC, Agent Card, message/send/tasks/get; client implemented independently) to a standalone specialist agent (securities/law), which never lowers the review requirement (pinned by tests).
• Evaluation-driven across ten analysis rounds; an independent review and blind tests uncovered a security defect that nine automated runs had missed.
• Voice AI frontend, responding live: covered cases are answered during the conversation, while sensitive cases are escalated before generation; measured response latency < 7 s (local GPU STT/TTS).

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

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

• Genuinely agentic with LangGraph: ReAct agent with four tools and conversation memory – the model decides itself whether to use the manual (RAG, Chroma), a knowledge graph (GraphRAG, Neo4j/Cypher – decoding warning lights), or a workshop/booking service.
• Human-in-the-loop before the irreversible action: before every appointment booking, the graph pauses (interrupt) and obtains the driver's explicit confirmation – the same approval-before-action discipline as in BankingGPT, in a different framework.
• Eval as a CI gate: three-part scorecard (RAGAS grounding + deterministic tool-routing accuracy + DeepEval safety: does the answer mention the warning first in the case of 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.