Multi-Tenancy Expert

• Developed a pilot system to control and monitor multiple GoPro cameras
• Implemented start, stop, status, media, download and diagnostic functions via COHN endpoints
• Built camera detection, individual and group control, and stable session/KeepAlive logic
• Set up a download pipeline with a queue, retry handling and temporary files
• Ensured consistent session, folder and file naming for multicamera recordings
• Integrated provisioning, certificates and network operations

• Developed browser based platform for kubernetes no-code deployment and cluster management
• Developed CLI in Typescript to deploy the 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 & permission models for Keycloak, oAuth/OIDC, social login flows.
• Used LLM to convert user intent into the diagram.
• Worked on integration with multiple Sovereign Cloud like stackIt, Hetzner, CIVO, UpCloud plus public clouds like AWS, GCP, Azure
• The technology stack includes Java, SpringBoot, Kubernetes, OpenAI, Kubernetes multi-tenancy using vCluster, Karpenter, RBAC for CLI, Helm, React

Led the end-to-end integration and migration architecture for decommissioning SAP IS-U market communication and transitioning to Salesforce Marketing Cloud (SFMC) with E.ON IT Services — covering regulated EDIFACT market messaging, a three-phase data migration (transfer of market message inventory after cutover), redesign of market communication processes, and full GDPR and German energy-market compliance.

• Designed the three-tier target architecture (SAP IS-U → NScale B2B gateway → SFMC) processing 50,000–100,000 EDIFACT messages daily within sub-5-minute SLAs.
• Architected the three-phase data migration: 36 months of historical data, zero-loss cutover of in-flight market messages, and near-real-time CDC synchronization.
• Delivered secure, BDEW/GDPR-compliant integration (AS2/OFTP2, RFC/IDoc, REST APIs, OAuth 2.0, Azure AD, AWS S3) achieving >99.5% uptime, <0.1% migration discrepancy, and RTO <4 hours.
• Applied BPMN to model and optimize the market communication processes.

Technologies: SAP IS-U, NScale, Salesforce Marketing Cloud, EDIFACT, OAuth 2.0, Azure AD, AWS S3, BPMN, Jira, Confluence, Draw.io

As a Council Member at GLG (Gerson Lehrman Group), the world’s leading expert network, I provide organizations, investment firms, and consulting companies with expert discussions on demand – wherever specialized knowledge in information security, IT governance, and regulatory compliance is needed.

My assessments are based on many years of practical experience in highly regulated industries: from building and implementing information security management systems (ISMS according to ISO 27001), IT risk and vulnerability management, and business continuity (ISO 22301) to the practical implementation of European regulations such as DORA, NIS2, BAIT, and the Cyber Resilience Act (CRA).

The cooperation is project- and discussion-based. I provide decision-makers with a practical perspective gained from real-world experience on cyber risks, security governance, and operational resilience – exactly when it is needed.

• Opt-in RAG extension over tenant-owned data sources (SharePoint, Confluence) on existing multi-tenant enterprise AI platform
• Architecture: ADRs, solution evaluations, permission strategy, cost modeling
• End-to-end SharePoint and Confluence connectors: OAuth consent flows, token refresh, metadata sync, search integration
• Permission resolution: ACL indexing at ingestion and query-time verification (document-level security)
• Elasticsearch hybrid search (semantic + keyword) with RRF scoring
• RAG chat with context injection and source citations
• Stack: Elastic Cloud, Elasticsearch, Docker, Northflank, Next.js, React, TypeScript, Prisma, Microsoft Graph API, Atlassian REST API, OAuth 2.0

• Designed and implemented modular AI assistants for sales and business processes within the Microsoft ecosystem (Agentic AI, Copilot extensions)
• Frontend architecture and development with React + TypeScript for embedded chat and assistant surfaces (streaming UI, Hooks, React Query, OpenAPI clients)
• Enterprise-level agent development: reusable skill/agent library, MCP servers, review and compliance gates
• LLM integration into the user experience: Anthropic (Claude), OpenAI, tool use, RAG pipelines, prompt engineering, guardrails
• Architecture and code review consulting, and mentoring within the AI development team
• Integration with Microsoft Graph, Power Platform, and Azure services
• Technologies: React, TypeScript, Anthropic Claude, OpenAI, MCP, RAG, Microsoft Graph, Power Platform, Azure

Multi-Agent Document-Generation Platform

Problem:

Turn a single prompt into a well-researched, structured and cited document, while keeping the user in control: every stage can be reviewed, corrected or revisited before the system moves on.

Architecture:

A multi-agent system orchestrated by a central controller. More than 20 specialised pydantic-ai subagents (understanding, structuring, planning, research, writing, assembly, cross-reference check, glossary, citation, reference table and more) pass results forward through a shared plan persisted in Postgres (asyncpg); a runner layer dispatches each task by name to its agent, and mechanical steps such as formatting, table of contents and list of figures are deterministic code instead of LLM calls. Provider (Anthropic or OpenAI) is a configuration setting, and responses stream over Server-Sent Events.

Hosting & Infrastructure:

Stateless container run as a Scaleway Serverless Container on a private network with managed PostgreSQL, object storage for finished documents and assets, and centralized log shipping (Loki / Scaleway Cockpit), provisioned with OpenTofu modules and deployed through GitLab CI; usage is metered per API key.

My Contribution & Key Decisions:

• Central decision controller: a satisfaction classifier turns the user's free-text feedback into a verdict (keep working, advance, cancel or revise an earlier task), and a middleware applies it to the plan. Plan progression supports jumping back to earlier tasks and re-running the stages after them.
• Research and writing fan-out: planning produces a plan from which a research-design agent generates individual research tasks and a writing-design agent generates individual writing tasks, each linked to the research it needs. Every task runs in its own dedicated agent with its own conversation history.
• Self-review and human-in-the-loop: after each step a critical-thinking agent reviews the output; the user can accept, refine, or ask questions about a critique before the plan advances.
• MCP integrations: two remote MCP servers, web search and internal document search, connected through pydantic-ai with retries and long-running tool-call timeouts. Classifier agents decide per task whether web search is needed, and a small model condenses raw search results into structured findings before they reach the writing agents.

Usage Metering:

Clients authenticate with an API key validated against a key-management service; consumption is charged in credits calculated from token usage per model plus a markup, and exhausted quota is answered with HTTP 429.

• Managed the successful overall Trial and Commercial deployment of OpenRAN technology and swap-out of legacy SRAN for 2 mobile network operators in Germany.
• End-to-End Project life cycle governance and coordination of multiple Workstream leads i.e. Operations, Performance, Site Solution Management, Design, SW Delivery, Integration & Implementation, OSS Tools, 3rd-party Resource Support.
• Project planning to cover major milestones by delivering roadmap alignment in compliance with the German Network Regulatory Agency (BNetzA), as a vendor.
• Provided pre/post-Sales support to the Accounts Team for RfP/RfQ submissions.

• Led discovery phase and POC for Shopware to Shopify Plus migration across EMEA markets, evaluating platform suitability, technical architecture, and multi-brand/multi-country capabilities against business requirements.
• Designed reference architecture for Shopify Plus implementation incorporating headless front-end patterns (Vue.js, Nuxt.js), CMS integration (Magnolia), and Azure middleware (APIM, Functions, Logic Apps, Service Bus) for 11 EMEA markets.
• Defined migration strategy analyzing data mapping, cutover approach, and zero-downtime deployment patterns using Varnish caching, GitOps pipelines, and CI/CD orchestration across six vendor teams.
• Architected multi-tenant Shopify Plus governance model with centralized admin, localized storefront customization, and compliance controls (GDPR, data residency).
• Prototyped AI-driven search optimization (LLM.txt, JSON-LD) for product discoverability in Google AI results, demonstrating post-launch performance opportunities.
• Defined EMEA expansion roadmap for 15+ markets through C-level strategic workshops, identifying phased rollout, market-specific configurations, and resource requirements.
• Tech Stack: React, Nuxt.js, Vue.js, Magnolia CMS, Shopware, Shopify Plus, Azure (APIM, Functions, Logic Apps, Service Bus, Front Door), Varnish, SAP, MS Dynamics, Docker, Kubernetes, GitHub Actions, PostgreSQL, Kafka

• Clarification of project objectives, scope and the target business vision for building the AI-based knowledge database.
• Derivation of the initial architecture and implementation strategy for the Zasterbot chatbot, including separation of the MVP and further development stages.
• Development of a target business vision for building a structured knowledge database and integrating a future chatbot.
• Derivation and prioritization of use cases for information retrieval and provision by the chatbot.
• Modeling of data structures and flows for the effective organization of the knowledge database on the Base44 platform.
• Design and implementation of data models for storing and linking relevant information.
• Development of processes for extracting, analyzing and preparing raw data for the knowledge database.
• Ensuring data consistency and quality as the basis for the future chatbot.
• Planning the integration of Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) for precise and context-specific answers.
• Implementation of functions for analyzing and displaying data from the knowledge database.
• Use of the Base44 platform with JSON Schema-based entities and a flexible permission concept.
• Implementation of Deno functions for backend logic, event processing and connecting external APIs.
• Integration of OpenAI services for initial data analysis.

Procure Ai builds a procurement platform with tools to optimise purchasing and supplier management, delivering real-time analytics, cost-saving insights, and automated workflows. A common data model integrates and enriches data from multiple ERP and e-procurement systems including Ivalua, SAP, Coupa, WPS, and Jaggaer.

06/2025 – TODAY:

• Architecting and building a new AI-native procurement platform with document intelligence, an agent orchestration layer using Mastra and LLM-based workflow automation across supplier, intake and category management use-cases
• Shipped agentic engineering workflows across the development team, enabling LLM-assisted code generation and review automation, measurably reducing cycle time on repetitive development tasks
• Migrating the Design System from Material UI to shadcn/ui with Tailwind, improving consistency and reducing frontend build overhead
• Staying hands-on across frontend, backend and AI features while the engineering team grew from 10 to 20+ engineers: hiring, onboarding, 1:1s and mentoring

06/2020 – 06/2025:

• Joining as the first engineer after the two founders; shaping platform architecture and product vision from scratch in close collaboration with the CTO, growing the platform to serve 10 enterprise customers
• Leading fullstack feature development on the core procurement platform, with focus on Analytics, Search, and Autonomous Negotiations use-cases: defining MVP scope, aligning technical decisions to customer outcomes, and cutting work that wasn't delivering value
• Challenged a field-based configuration request for Autonomous Negotiations and instead built a node-based rule builder matching how category managers think in conditions and branches; later reused across other workflow and decision configuration use-cases
• Designing and implementing multi-tenant authentication and fine-grained authorisation based on organisational units
• Architecting and building a multi-tenant Admin Application for managing customer installations across environments, covering configuration, feature flags, and i18n
• Creating and maintaining a custom Design System built on Material UI, used across the full product
• Setting up and maintaining CI/CD pipeline and full QA suite (linting, unit, integration, and e2e testing)
• Architecting and implementing a multi-environment release process using Helm and Helmfile; owning infrastructure as code across AWS and Azure
• Researching and piloting new tools and frameworks; making build-vs-buy decisions to balance velocity, cost, and long-term maintainability
• Grew the engineering team from 4 to 10+ engineers, mentoring engineers and building a culture of ownership, code review and iterative delivery

Technologies: TypeScript, JavaScript, React, Node.js, Fastify, GraphQL, GraphQL Codegen, GraphQL Mesh, GraphQL Yoga, Hasura, Apollo Client, REST, CubeJS, PostgreSQL, Prisma, Elasticsearch, Meilisearch, Typesense, Kafka, Avro, Karapace, Kubernetes, Docker, Terraform, OpenTofu, Helm, Helmfile, GitLab CI, Keycloak, Better-Auth, OpenFGA, Nx, Vite, Vitest, Playwright, Testing Library, Storybook, Chromatic, Material UI, shadcn/ui, Tailwind, React Flow, recharts, i18next, Backstage, Grafana, Sentry, Zod, Claude Code, Codex, Mastra, Vercel AI SDK, Vercel AI Elements, AWS, Azure

• Modernization of a large-scale Java enterprise application*

The project is modernizing a complex enterprise application that has grown over many years. The existing Spring-based legacy system runs on Java 8, OSGi, and Eclipse RCP and is being gradually migrated to a modern, maintainable architecture with Java 25 and Quarkus.

Marcus works on analysis, architecture, refactoring, and implementation. One focus is on untangling historically grown structures and dependencies and on building a clean, sustainable Java and Quarkus technology stack.

Tools & technologies: Java 8, Java 25, Quarkus, Hibernate ORM with Panache, EclipseLink, OSGi, Eclipse RCP, Maven, JUnit, Mockito, REST, JSON, Git, Eclipse IDE, IntelliJ IDEA Ultimate, Jira, Confluence

• Automated Kubernetes deployments to over 400 customer target environments (Rancher/RKE2) using versioned Helm charts and Argo CD ApplicationSets for daily releases.
• Created self-service customer onboarding based on versioned runbooks, reducing the process from days to hours; coordinated with customer IT teams (AD/LDAP, SMB/DFS, network).
• Migrated selected services to AWS alongside the Open Telekom Cloud platform: provisioned VPC, EC2, and IAM roles with least-privilege policies using Terraform; operated workloads on EC2.
• Set up Keycloak realms and OIDC/SAML clients for product SSO, federated with customers’ Active Directory.
• Set up tenant-specific strongSwan IPsec sidecars on Kubernetes instead of a central transit VM, with keys in HashiCorp Vault: reduced connectivity costs by approximately 80%, with DFS indexing over the tunnel.
• Designed the high-availability migration of the Redis environment to managed OTC DCS; set up alerting and on-call rotations with incident.io by severity, and improved Grafana queries and indexing.