Renovate Experts in Germany

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.

IT consulting, analysis, architecture design, new and further development, code review, test automation, continuous integration, continuous delivery in backend and frontend areas for Automotive Project Instavalo.

Frontend:

• Implementation of UI components according to specifications, especially style guides and responsive design eith React and Typescript
• Component testing
• Code documentation
• CI/CD with Gitlab Pipeline

Backend / IoT:

• Analysis and architectural design with AWS Greengrass IoT on Edge Devices
• Setting up Microservices containers with Docker Compose on Edge device with AWS Greengrass and AWS IoT IAM, Token Exchange Service, Ansible
• CI/CD with Gitlab Pipeline, Terraform, AWS ECR
• Logging with Fluentbit Lua Language for AWS Cloudwatch
• Python Lambda for AWS Greengrass Recipe deployment on Edge Devices
• Implementation of test-driven development with JUnit, Mockito, and code Coverage
• Jacoco
• Definition of REST interfaces with OpenAPI / Swagger
• Development and enhancement of software based on Java Quarkus, Typescript NestJs NodeJs and Python
• Authentication and authorization in Aws IAM
• Development of REST and gRPC interfaces for the frontend and backend
• Implementation of Maven dependencies with DevSecOps OWASP
• Spring AI, Jetbrains AI Assistant, Junie, Github Copilot, Claude Code, Agents, Skills, Command, Hooks, Subagents

Transmission system operator – network provisioning platform (team lead)

• Designed the saga orchestrator in Python that provisions network fabrics with rollback.
• Split IP, identity, and resource allocation into bounded contexts with their own databases and typed clients.
• Implemented data access using DDD repositories and units of work, with no SQL in the domain code.
• Required integration tests using real PostgreSQL and RabbitMQ containers, and API fuzzing for every service.
• Introduced an agent workflow where a spec starts each change and a human approves every merge.
• Rolled out OpenTelemetry auto-instrumentation through GitOps across eighteen Kubernetes clusters.
• Led incident response for stuck provisioning and recorded every outage as a post-mortem.

Languages and software used: Python, FastAPI, Pydantic v2, SQLAlchemy async, PostgreSQL, RabbitMQ, Celery, pytest, testcontainers, schemathesis, Helm, Flux CD, GitLab CI, OpenTelemetry, pi coding agent.

Software product company – datacenter simulation SaaS (backend development)

• Built the asynchronous simulation pipeline as the second-largest contributor among more than twenty team members.
• Tagged every image by commit SHA and semver in the GitHub Actions deployment workflows.
• Diagnosed the RabbitMQ memory alarm that froze every simulation and fixed the limits in the Helm chart.
• Converted the test suite to function-style pytest, with coverage reported in every pipeline.

Languages and software used: Python, FastAPI, SQLAlchemy, Alembic, Celery, RabbitMQ, Redis, PostgreSQL, S3, EKS, Helm, Keycloak, GitHub Actions, pytest, mypy, ruff, SonarQube.

Internal AI platform – model serving and telemetry

• Built the FastAPI service that deploys open-weight models on GPU tiers as OpenAI-compatible endpoints.
• Upgraded production EKS by two Kubernetes minor versions and fixed zone-bound storage faults.
• Traced every model call, including its token count, cost, and latency, through the OpenTelemetry operator.

Languages and software used: Python, FastAPI, vLLM, LangGraph, pydantic-ai, OpenAI and Anthropic APIs, EKS, Helm, Flux CD, Terraform, GitLab CI, OpenTelemetry, Grafana.

• work in the Developer-Experience team to improve developer experience and tooling for all teams of the RTL+ streaming platform
• development of reusable GitLab CI/CD components to standardize processes and automatically enforce code quality and security gates
• infrastructure automation with Pulumi
• operation and monitoring of GitLab Runners in AWS with Kubernetes
• integration and automation of Renovate in GitLab pipelines for continuous dependency updates
• extension of Backstage as the central developer platform to optimize internal workflows and self-service capabilities
• development of various tools and automations in TypeScript, Go, and Python

• Implemented the entire reporting ecosystem from scratch using Power BI and Fabric as a tool for several clients
• Guided clients on how to implement their own reporting system
• Main industry is E-Commerce

• Hands-on solution architect
• Digital product development - SaaS
• Strategic consulting on software architecture, cloud migration, and DevOps processes
• Coaching SE developers and IT architects

• Responsible for the entire software architecture of the parental allowance portal
• iOS and Android app with React Native and Expo, incl. push and OTA updates
• Store releases via App Store Connect and Google Play Console
• TypeScript monorepo for app, website and backend, web with Next.js and Tailwind
• Own promo, voucher and discount engine with contact and segment logic
• Payments via RevenueCat and in-app purchases, authentication with BetterAuth
• REST APIs based on OpenAPI, PostgreSQL with Prisma and Drizzle
• Self-hosting on Hetzner with Docker, Coolify, Terraform and GitHub Actions
• Tests with Vitest, Playwright and visual regression via Chromatic
• Observability via Grafana Cloud and error tracking with Sentry
• Performance marketing via Meta Ads, measured with custom event tracking
• Grew the product to 20,000 app users with a purchase rate of almost 12 %
• Managing Director since 04.2025, responsible for product and technology

I implemented a Zero-Trust architecture for robust, military-grade maritime container mini data centers based on VMware & Tanzu to support containerized GIS workloads for ground forces. The main focus was on securing communications, workload protection, and data access in contested electronic battle environments affected by jamming, interception, signal manipulation, and constantly changing operational conditions. I designed and architected use cases so that every element of workload, identity, and system could continue to operate independently and securely even in degraded or disrupted scenarios. In parallel, I defined the enterprise and solution security architecture with LeanIX, Bizzdesign, and HOPEX as enterprise architecture, repository, and governance platforms to maintain architecture inventory, relationships, traceability, target pictures, and security governance in complex environments. For the architectural designs, I used Sparx Enterprise Architect to describe formal architecture views, interfaces, trust boundaries, and system architecture in both IT and OT environments. IriusRisk was used for threat modeling of the solution to identify architecture-driven risks, derive security requirements, and detect countermeasures and design gaps directly from the solution models. Risk and compliance management was supported with Archer. Architecture decisions, control gaps, and operational risks were translated into controlled governance and auditable compliance measures. For documentation, collaboration, and visual design, I used Confluence to maintain Architecture Decision Records, Security Blueprints, and workflows. I used Lucidchart and draw.io to create design artifacts tailored to stakeholders. I also defined OT security concepts with support from electrical and mechanical engineers in the areas of oil, vehicle onboard systems, rail, power plants, pharma, gas turbines, and nuclear technology. I created the end-to-end OT security strategy, starting with global policy, developed into standards and procedures, and finally aligned with Bell-LaPadula, Purdue Model, SABSA, TOGAF ADM, CENELEC 50701, IEC 62443, and NIST standards. In addition, I worked with engineering team leads to identify critical KBP assets and place them under protective measures that segmented SCADA, PLC, and HMI assets. I drove collaboration between Security, IT, and OT teams to create standardized workflows and use cases for the OT security solution catalog, while integrating Defense-in-Depth and Zero-Trust principles into operational environments. A key part of my work was integrating multidisciplinary engineering, security, and operations stakeholders into a unified security blueprinting strategy and ensuring that architecture, threat modeling, governance, and documentation were technically strong and operationally practical.

• Bootstrapping a CloudOps team and building a multi-cloud provider backend for a low-code Internal Developer Platform (IDP) with env zero

• Introducing user story mapping, ADRs, milestones, and backlog management

• Designing and developing core APIs, setting up CI/CD pipelines, OpenTofu/Terraform scripts

• Representing and communicating the team with third-party stakeholders (e.g. env zero)

• (Cross-)team coaching on DevOps, software design, Terraform, Golang, and agile practices

• Setup and operation of a multi-cluster AWS EKS platform for banking workloads with a unified network and security architecture across 45 AWS accounts.
• Developed and standardized a unified AWS network and security architecture for 45 AWS accounts, enabling consistent governance, connectivity, and compliance for enterprise customer environments.
• Developed and operated a multi-cluster AWS EKS platform to support production workloads, significantly improving scalability, availability, and operational reliability.
• Implemented a GitOps deployment model using ArgoCD and Helm, enabling fully automated, auditable deployments and reducing manual release errors.
• Automated infrastructure provisioning using Terraform and Terragrunt at scale, reducing environment setup time by up to 70% and eliminating configuration drift.
• Established enterprise-grade backup and disaster recovery strategies using Velero and AWS Backup, ensuring reliable multi-cluster recovery and business continuity.
• Introduced Rancher as a self-service Kubernetes platform, accelerating developer onboarding while maintaining centralized security and governance.
• Designed and implemented detailed AWS IAM concepts (roles, policies, trust relationships) to enforce the principle of least privilege for access to accounts, workloads, and CI/CD pipelines.
• Developed AWS Lambda-based pre-provisioning workflows for databases, automating initialization, configuration, and access setup to support secure and consistent application integration.
• Delivered consistent, high-quality results as part of a 5-person AWS Solutions Architecture team, resulting in three consecutive contract renewals.

• Due to an organizational restructuring towards product-based teams, the implementation of a Data Mesh in the area of Digital Supplier Management (DSM) was decided.
• A highly available real-time Data Mesh for providing large volumes of data via Kafka and REST to other products.
• New development of a core supplier management software in a (micro-)service-based architecture with a modern tech stack.
• Technologies/Tools:
• Java 21
• Spring Boot
• Angular
• TypeScript
• Go
• MapR
• Kafka
• Docker
• Google Cloud Platform (GCP)
• Kubernetes
• Helm
• GitLab CI
• Maven
• JUnit
• Mockito
• WireMock
• Cypress
• Keycloak
• OAuth 2.0 & OpenID Connect
• Humio
• Nexus
• Artifactory
• SonarQube
• Renovate
• Git
• Postman
• IntelliJ

• Implemented the frontend and backend of a chat application for an AI startup
• Used Go and Dart
• Technologies: gRPC, Flutter, Terraform (IaC)
• CI/CD via GitHub, deployment on Google Cloud Run

• Refactoring test automation (Java/Kotlin)
• Implementing integration tests (Cucumber, Gherkin)
• Bug fixing and implementing new features in pair programming
• Implementing test processes in CI/CD architecture (GitLab)
• Planning and creating a test strategy
• Analyzing business processes to assess test coverage
• Bug tracking and verification (Kubernetes/k8s, Kibana)
• Extending the deployment pipelines in GitLab CI
• Evaluating logs and metrics
• Implementing tests to verify security requirements (PCI DSS/ISO 27001)

• Supported implementation and operation of a portal used online and offline in customer-facing vehicles
• Automated processes by introducing CI/CD pipelines
• Provided enablement and methodological guidance for adopting software engineering best practices
• System environment: NestJS, Node.js, npm, AWS, Docker, Docker Swarm, GitLab CI, WhiteSource, PostgreSQL, Prometheus, Grafana, OpenSearch, REST API