Model Context Protocol Experts in Germany

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

• 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.

• Built a scalable nearshore IT developer hub (Croatia, Czech Republic, Poland) as an independent company through a BOT model (Build – Operate – Transfer)
• Identified, selected, and managed full-service agencies; introduced management and control mechanisms, including KPIs, SLAs, and regular service reviews
• Prepared and reviewed data processing agreements and framework contracts in coordination with Legal & Compliance; integrated regulatory requirements (including KRITIS) into process design
• Advised on cloud vs. on-premise strategies, data storage, and authorization concepts; supported Procurement with tendering and service provider evaluations
• Managed change and process harmonization between internal teams and nearshore partners; reported to executive management, CFO, and CIO

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

• Repaired a broken “ScrumBan” process, then established a pure Kanban system; increased output in the Kanban flow by 22% within four weeks

• Increased team autonomy and decision-making ability by implementing new decision strategies; resulting in up to 25% better outcomes

• Redesigned retrospectives (including one-to-one coaching and workshops), which led to consistent implementation of the resulting action items

• Intensive coaching of Product Owners (POs) to develop and support “Empowered Teams”, alongside leadership development to place agile frameworks and methods in a realistic context (“de-illusioning”)

• Supported change management processes to promote an agile company culture among management and teams, improving internal communication to increase transparency and effectiveness in agile processes

Project: Defect Generation on Test-Bench Images of Metal Surfaces Environment: Automated Visual Inspection (AVI), Metallurgy & Manufacturing

• Objective & Implementation: Designed, architected, and trained Generative Adversarial Networks (Pix2PixHD / SPADE) for image-to-image transformation. Targeted generation of synthetic material defects (e.g., cracks, inclusions, scale) on rough metal surfaces under real test-bench lighting conditions for privacy-compliant and efficient dataset expansion (data augmentation).
• Technical Design: Implemented robust Generative AI and computer vision pipelines in Python and PyTorch. Used semantic segmentation approaches for mask-controlled defect synthesis and subsequent evaluation with EfficientDet object detection models.
• Business Impact: Massive dataset upscaling (10x) without time-consuming and costly physical test-bench runs, while significantly improving the detection performance of automated inspection systems.

Technologies & Skills Used: Python | PyTorch | SPADE | Pix2PixHD | EfficientDet | Machine Learning | Semantic Segmentation | Computer Vision

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 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

• 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

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.

• 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

• Built an MCP (Model Context Protocol) layer for Mwanachama's agency service, turning domain manager methods into callable AI-agent tools. This included a composite tool that builds a full organization design (org chart, goals, workflows, RACI matrix) from one specification.
• Built the chat-driven agency builder (Wakala Studio and API), where an organization describes its structure in natural language and an AI agent uses those tools to construct and modify the live design.
• Added an insights service so an organization can review AI-agent interactions and completed work. Insights from that review feed back into solution design, gated by architect and user sign-off.
• Alongside this, designed and built the platform itself: ~20 Go microservices on PostgreSQL, Flutter and React clients, deployed on Kubernetes.
• AI agents scan the platform autonomously for security gaps and run scripted tests, covering API (Postman-style) and UI testing. The rest of the work stays supervised. No rogue agents, promise.
• Building an AI-native enterprise platform that structures organizational data, workflows and responsibilities for both people and AI agents.
• Models accountability through RACI, allowing human and AI participants to take different operational roles, including Responsible, Accountable, Consulted and Informed. AI agents can also take controlled approval roles where the organization assigns that responsibility.
• Extended the organizational and operational-risk themes from my Executive MBA thesis into software, making roles, processes and controls explicit and machine-readable.
• Structures enterprise context so LLM interactions use more relevant information instead of repeatedly processing large amounts of unstructured content.

• Drove key experience streams in the redesign of a large-scale telecommunications e-commerce platform focusing on mobile plan selection, product configuration, and digital contract completion.
• Delivered scalable Figma-based white-label solutions within a multinational Scrum setup to enable efficient multi-brand rollout.

• Recurring problem in my own AI-assisted projects: requirements analysis, use cases, and architecture decisions can be created quickly with AI support, but remain difficult to follow and 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, verifiable data instead of plain text: requirements, use cases, and architecture decisions form a consistently linked knowledge graph, traceable from requirement to architecture decision – queryable by both people and AI agents. Technically based on RDF/OWL and a custom MCP server.

• Result: Working MCP daemon, Docker image published automatically to GHCR, nine hexagonal modules, eleven ADRs (including an Open-Core licensing model). Requirements engineering and Ubiquitous Language hexagons are active. Public as a Community Edition under Apache-2.0 since 07/2026 (github.com/kogn-io/arknet), together with the Claude Code plugin and 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

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