Retrieval-Augmented Generation Experts in Germany

• Redesign of the company's BI infrastructure: replacement of a fragmented landscape of manually maintained Excel solutions and CSV imports with a centralized Power BI environment featuring a unified data model as the company-wide single source of truth
• Consolidation of previously isolated reporting logic into a central semantic model – eliminating redundant files, manual data transfers, and inconsistent metrics between departments
• Forecasting & planning: Design and implementation of company-wide liquidity planning in Power BI – from business logic to a fully automated, data-source-driven planning model replacing the previous manual Excel process; enables rolling forecasts and continuously up-to-date cash flow transparency for management
• Optimization of existing Power BI dashboards in terms of performance, structure, and analytical value using an AI-native approach
• Analysis and improvement of the data model, including data quality analyses, data cleansing, and consistent modeling using star schema, DAX, and Power Query
• Incident & anomaly analysis: Identification, investigation, and explanation of data anomalies, including root-cause analysis and concrete recommendations for action
• AI solution architecture: Connecting Business Central and Power BI to LangDock via MCP (Model Context Protocol) for AI-supported data usage
• Creation of a historical data layer as a basis for trend and time-series analyses
• AI-supported automation: Design and development of AI skills, agents, loops, and processes for the automated analysis and interpretation of reports
• Automated reporting workflow: Setup of scheduled, automated email distribution of AI-generated analyses and recommendations to stakeholders
• Gathering and documentation of business requirements and coordination with business departments and IT as part of requirements engineering / product owner activities
• Breaking down overall requirements into clearly defined work packages and tasks
• Definition, prioritization, and management of milestones throughout the entire project lifecycle

Tools: POWER BI, M365, Copilot Studio, MIRO, Microsoft Business Central, Microsoft Fabric, Claude AI, ChatGPT, LangDock, MS VS Code

Remote freelance role focused on Agentic AI strategy, secure application patterns, and reusable agentic workflows for a government agency.

• Development and implementation of an open-source Agentic AI strategy for a government agency, with a focus on GDPR, security, and self-hosted solutions
• Development of reusable agentic workflows and business applications that enable non-technical employees to solve business problems independently
• Implementation of nine business applications with Single Sign-On (SSO) and Azure PostgreSQL integration on Hetzner Linux servers

Techstack: Python, Streamlit, Anthropic SDK (Claude), Azure, Linux, PostgreSQL, MS SQL, Angular

• Support for a data, analytics and AI initiative in a regulated enterprise environment by structuring, evaluating and prioritizing several data-driven use cases based on business impact, feasibility, scalability, data maturity and governance requirements.
• Translation of complex business and analytics requirements into clear product, data and implementation logic, as well as preparation of decision-ready documents, target visions and roadmap inputs for stakeholder and management discussions.

• 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.

• Planned and developed a CPU monitoring application for monitoring system performance and resource utilization.
• Designed and implemented a Spring Boot backend providing a REST API for processing and exposing monitoring data.
• Developed the React frontend for presenting monitoring information in a clear and user-friendly interface.
• Integrated PostgreSQL for persistent storage and management of application data.
• Containerized the application and its services using Docker Compose.
• Automated infrastructure provisioning and deployment using Terraform on AWS.
• Structured the application as a modern, maintainable system using REST-based communication between frontend and backend.
• Designed and developed a secure, scalable CPU monitoring architecture (cpu-watcher) with a dedicated collector application that streams monitoring data to the backend, reducing direct exposure of system resources.
• Designed a secure cloud infrastructure with the database isolated within a private network and OIDC-based authentication.
• Implemented Infrastructure as Code with Terraform and integrated version-controlled CI/CD pipelines to automate testing, infrastructure changes, and application deployments.
• Designed and implemented the frontend delivery architecture using AWS CloudFront.

Stack: Spring Boot · React · PostgreSQL · REST API · Docker Compose · Terraform · AWS

AI-supported document processing and inventory management integration

Design and development of an AI-supported application for the automated processing of delivery and invoice documents, connected to SelectLine ERP. Documents are analyzed using AI, matched with orders and line items, and prepared for posting goods receipts.

IMPACT:

• Automated extraction of structured order, delivery and invoice data from PDF and image documents
• Automatic and manual mapping of documents to orders and order line items
• Integration with SelectLine ERP for order import, status synchronization and goods receipt postings
• Traceable processing through separate analysis, mapping and posting processes as well as technical logging
• Development of a containerized end-to-end architecture with AI analysis, workflow automation and relational data storage

KEYWORDS: AI, document analysis, OpenAI, n8n, SelectLine ERP, FastAPI, Python, JavaScript, MariaDB, Docker, REST API, PDF, OCR, mapping, inventory management, goods receipt, workflow automation

• Development of an agent-based governance platform for the automated assurance of EU AI Act compliance and ODA-compliant orchestration of AI services in complex enterprise environments.

• Design and implementation of an agent-based "Mission Control" framework (Aletheia Conductor) for autonomous state monitoring and process control.

• Development of "Compliance-as-Code" (CaC) solutions based on OPA/Rego for system-wide enforcement of regulatory guardrails.

• Integration of TM Forum ODA standards (TMF630, TMF622, TMF642) to ensure interoperability and standardization.

• Building a highly available event-driven architecture using Redpanda and CloudEvents v1.0 for near-real-time event processing.

• Implementation of an audit-proof "Evidence Chain" through cryptographic linking of trace logs in preparation for automated audits.

• Tech Stack: Java 21 (Quarkus Native), TypeScript (Next.js), Redpanda (Kafka API), CloudEvents v1.0, OPA (Open Policy Agent) & Rego, TimescaleDB, ZincSearch, Redis, TM Forum ODA, Git, GitHub, Clean Code Development, Like-C4.

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.

• Following the turnaround completed in 2025, the company is pursuing a growth target of more than €50 million in revenue by 2030, driven by the Datacenter First strategy, efficiency gains through AI and a restructuring of sales. This required a market-oriented product portfolio and documented and automated processes from lead to invoice.

• Restructuring of the product portfolio for data centre, colocation and cloud.

• Analysis of market drivers and growth areas for portfolio and pricing decisions.

• Documentation and optimisation of processes from lead to invoice and up-selling.

• Introduction of AI-supported systems in sales and marketing to automate these process steps.

• Regulatory assessment of AI use, particularly for customers from the banking sector.

• Redesigned product portfolio for data centre, colocation and cloud as the basis for growth planning.

• Fully documented process map from lead generation to invoicing.

• Prioritised AI use cases for sales and marketing with a regulatory assessment for each use case.

• Established governance for the use of AI in a critical infrastructure environment.

• Alignment of product, sales and marketing management based on shared KPIs.

Stabilization of 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

• Designed and moderated a NIS2 preparation workshop for RAS Reinhardt Maschinenbau GmbH and its IT service provider Catuno GmbH. Together with executive management and IT leadership, the current status was assessed, an initial GAP analysis was conducted and areas for action were prioritized based on ISO 27001.
• Developed an ISO-27001-based regulatory framework (ISMS) for NIS2 compliance, including a structured current/target GAP analysis, targeted improvement of the security maturity level and preparation of the organization for NIS2 audit readiness.

• 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.

• Fully on-premises LLM document-examination platform for a compliance-critical banking domain: agentic LangGraph pipeline with deterministic verification, every AI judgment structured and source-anchored; ~960 automated tests, zero data egress
• GPU throughput engineering (quantized serving, speculative decoding, prefix caching): 9.5x extraction speed-up, 500+ multi-document case files per day on a single A100
• AI-native EDI/EDIFACT integration platform (~116k LOC Java 25 / Spring Boot 4, 1,900+ tests): LLM-drafted partner mappings machine-verified before go-live (DFDL conformance, field-coverage checks, dry runs), ~99.5% byte match on real customer files — replacing weeks of manual mapping per partner

• Relaunched a self-developed semantic name recommendation product by combining semantic search, graph-based similarity analysis, LLM-/RAG-supported content, and AI-assisted development processes.
• End-to-end responsibility across the product lifecycle—from use case definition and solution design through prototyping and evaluation to the iterative development of the roadmap.
• Evaluated AI use cases in terms of user value, technical feasibility, data quality, governance, and operating costs to guide MVP scope, roadmap decisions, and continuous product improvement.