Large Language Model Experts

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.

• Setup of a scalable nearshore IT developer hub (Croatia, Czech Republic, Poland) as an independent company through a BOT model (Build – Operate – Transfer)
• Identification, selection, and management of full-service agencies; introduction of control and governance mechanisms including KPIs, SLAs, and regular service reviews
• Creation and review of data processing agreements and framework contracts in alignment with Legal & Compliance; integration of regulatory requirements (incl. KRITIS) into process design
• Consulting on cloud vs. on-premise strategies, data storage, and authorization concepts; support for procurement in vendor selection and provider assessments
• Change management and process harmonization between internal teams and nearshore partners; reporting to management, CFO, and CIO

Result: Scalable IT developer hub with an audit-proof governance model, reduced operating costs, and faster product development.

• Developed a browser-based platform for Kubernetes no-code deployment and cluster management
• Developed a CLI in TypeScript to deploy resources in the cluster without leaving the browser UI.
• Implemented DevSecOps pipelines: image scanning, SBOM, policy enforcement, supply-chain security, and used Kyverno. Implemented IAM integration for the command-line utility tool.
• Designed role and permission models for Keycloak, OAuth/OIDC, and social login flows.
• Used LLMs to convert user intent into diagrams.
• Worked on integration with multiple sovereign clouds like StackIT, Hetzner, CIVO, UpCloud, plus public clouds like AWS, GCP, and Azure
• The technology stack includes Java, Spring Boot, Kubernetes, OpenAI, Kubernetes multi-tenancy using vCluster, Karpenter, RBAC for CLI, Helm, React

• Built a custom MediaWiki instance including installation, MySQL database, SSL, and automatic backups
• Set up user roles (Admin, Mod, Verified, User) and a permissions system
• FlaggedRevisions for editorial review workflow · comment and rating extensions

• Agile Transformation Coach within an SAP-driven End-to-End Lead-to-Cash program, supporting leadership and management teams in implementing and evolving the Sherpa Way of Working, strengthening Agile practices, role definitions and responsibility clarity (RACI), and delivery effectiveness
• Member of the leadership core team for the Way of Working, shaping and evolving agile operating models, challenging existing practices, and driving pragmatic, system-level improvements
• Conceptualized a Polarion-based Scrum Master dashboard as a single, role-based entry point for sprint status, dependencies, risks, and governance artefacts, reducing reporting overhead and improving transparency
• Provided targeted 1:1 coaching to the Master Scrum Master and Scrum Masters, strengthening leadership capability, role effectiveness, and support for team-specific challenges, including the redesign of Scrum Master syncs and collaboration formats
• Worked with teams and leadership on End-to-End Lead-to-Cash process analysis and documentation in SAP Signavio, supporting alignment, transparency, and a shared understanding of process expectations across teams

Stabilizing an Azure/.NET landscape in live operation.

• Architecture, DevOps, and operational readiness; technical decisions under time pressure
• Azure DevOps, monitoring, ETL/ELT, cloud security, FinOps, and data-mesh-related topics

Technologies: Azure DevOps, .NET, CI/CD, monitoring, FinOps

• Marketing Strategy: Lead the end-to-end analysis and evaluation of cross-channel marketing campaigns across the entire Customer Journey. My focus is identifying optimization potential and deriving clear, actionable recommendations that drive measurable business impact.
• Data Science & AI: Advanced predictive modeling (Churn, LTV), market basket analysis, clustering, and real-time AI-powered audience discovery utilizing RAG/LLMs.
• Marketing Analytics & Measurement: End-to-end attribution analysis, Marketing Mix Modeling (MMM), audience segmentation, conversion path analysis, and A/B testing across all major platforms.
• Data Engineering & Reporting: Designing and managing robust, multi-platform data pipelines (BigQuery, GCP) for data consolidation, automated dashboard generation, and critical API integrations.

• 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

• 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.

Product:

• Built a production-ready AI platform for generating brand-aware marketing images and videos from product data, user requirements, and uploaded media.
• Own the platform architecture, technical roadmap, API design, security, deployment workflow, operational reliability, and model-provider strategy.
• Developed the core platform in .NET and built supporting AI and workflow prototypes in Python, applying language-independent API contracts and structured interfaces between services and model providers.
• Implemented reliable background processing with RabbitMQ, persisted workflow state, idempotent handling, retries, failure recovery, logging, secure storage, authorization, and credit accounting.
• Made pragmatic build-versus-buy and model-routing decisions based on reliability, latency, cost, and maintainability rather than novelty.

Agent Orchestration & RAG Systems

• Built and compared agent workflows using Microsoft Agent Framework, LangGraph, and LangChain, including tool use, conditional routing, clarification steps, state management, and hand-offs between agents.
• Implemented reusable .NET components for agents, prompts, tools, model providers, structured responses, and retrieval with pyvector, making it easier to change AI providers without rewriting the core workflow.

AI telephone assistant platform

Claude Code, Google AI Studio, Python, LLM / Voice-AI, PostgreSQL

• Conception and hands-on development of an AI-supported telephone assistant platform (voice AI / LLM) – from idea and architecture to MVP/product.
• Built agentic workflows and full automations with Claude Code and Google AI Studio.
• Also delivered AI-supported work in client engagements: used Claude Code for governance documentation, requirement drafts, and automations.

• Task Engineering: Evaluating Coding Agents.
• Asset Creation: Building realistic task environments using datasets and files in German. Crucially, these assets must remain in the target language to genuinely measure multilingual handling.
• Prompting & Translation: finding failure points where AI does not work, in German.
• Implementation & Verification: Supporting the development of robust solutions (reference implementations) and write highly reliable, deterministic verifier scripts (using rubric-based judging only when strictly necessary).
• Calibration & Execution: Analyze execution logs and calibrate task difficulty (Easy to Very Hard) using standard Terminal-Bench run configurations against various model tiers (Haiku, Opus).
• Quality Assurance: Participation in a rigorous, 4-layer human quality control process (creation, human review, calibration review, and audit) alongside automated LLM-based checks to ensure fairness, grammatical accuracy, and benchmark integrity.
• Linguistic Review: Reviewing AI benchmark tasks across Hindi, Arabic, Japanese, Chinese, Czech and Turkish.

• Recurring problem in my own AI-supported projects: requirements analysis, use cases, and architecture decisions can be created quickly with AI support, but they remain hard to trace and are scattered across markdown files – knowledge is lost as soon as it is no longer in the context window. arknet turns requirements engineering and architecture knowledge into structured, testable data instead of plain text: requirements, use cases, and architecture decisions as a consistently linked knowledge graph, traceable from the requirement to the architecture decision – queryable for humans and AI agents alike. Built technically on RDF/OWL and its own MCP server.

• Result: MCP daemon running, Docker image automatically published on GHCR, nine hexagonal modules, eleven ADRs (including an open-core license model). Requirements engineering and ubiquitous language hexagon active. Publicly available as a Community Edition under Apache-2.0 since 07/2026 (github.com/kogn-io/arknet), together with the Claude Code plugin and the GHCR image; open-core model.

• Label: Java, Maven, RDF, RDF4J, OWL, SPARQL, Model Context Protocol, Spring AI, Docker, GitHub, Git, Claude Code, Obsidian, DDD, Hexagonal Architecture, ArchUnit, JUnit, AssertJ, interface development, Software Architecture, Continuous Integration, Knowledge Management

• Project management of the legal and system-side integration of Taschenkaufhaus into the Voxa group: conversion of all contracts, accounts, and system access rights on the defined cutover date
• Migration from Microsoft Dynamics NAV 2009 to 2013: analysis of all existing interfaces, redefinition of processes, and coordinated go-live without interrupting operations
• Integration of the complaints and returns process into MS Dynamics NAV 2013; major process simplification through standardization
• Introduction of a new POS system (Shopify POS) in all stores: requirements analysis, configuration, rollout, and employee training
• Use of n8n automation workflows for data reconciliation between marketplaces and ERP; manual processes significantly reduced