JSON Experts in Munich

• 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

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.

• 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

Temporary employment

• System black-box integration tests (BBIT, IVVQ): Execution of regression, release, acceptance, and compliance tests for safety-critical brake control units in the rail industry
• Software test application & integration: Runtime configuration of software components and libraries, validation of interfaces, configuration dependencies, and component interactions
• Test automation (FEAT framework): Co-development and further development of an automated test framework for test execution, reporting, and result analysis
• Functional safety (SiL4, FuSi): Ensuring compliance with safety requirements, traceability and coverage, as well as standards compliance according to EN50126/28/29
• Test automation for communication components: Configuration and validation of fieldbus (CAN) and Ethernet-based TCMS data communication interfaces (TRDP and CIP)
• Requirements analysis & shift-left (PTC Windchill ALM): Analysis of software and system artifacts to identify gaps, ambiguities, and redundancies early in the SDLC
• Test design & test case development: Derivation of test conditions, coverage strategies, and implementation of data-driven test cases (DDT), including reusable test data fixtures
• CI/CD & automation (Python, PowerShell, Jenkins, SVN): Automation of build, test, and HIL deployment processes as well as integration into CI/CD pipelines
• Test data & configuration management (XML): Maintenance and adaptation of XML test vectors and system configurations with automated integration into test environments
• Non-functional testing: Execution of performance and load tests to assess stability and system behavior
• Agile development & defect management (JIRA, Confluence): Participation in Scrum teams, test coordination, review of test artifacts, as well as defect tracking and root-cause analysis
• Error analysis & debugging (CANoe, CANalyzer): Analysis of errors and message flows across multiple system layers (application to bus)
• Model-based analysis (UML, Enterprise Architect): Specification of SUT/SOW and support for systematic test control
• Process & test documentation: Creation of integration and test documentation according to internal quality and certification requirements

Oracle Project Management and Automation

As part of the project, the operation of an Oracle infrastructure was automated by developing and enhancing Puppet modules and migrating existing Bash scripts to a standardized configuration management solution.

The aim of the project was to standardize and automate administrative processes, improve the maintainability of the Oracle platform, and increase the efficiency and traceability of infrastructure management through the use of Infrastructure as Code.

• Analysis and migration of existing Bash shell scripts to a Puppet-based automation solution
• Development and enhancement of Puppet modules for Oracle environments
• Automation of installation, configuration and operational processes using Infrastructure as Code
• Standardization and optimization of configuration management for Oracle systems
• Creation and maintenance of technical and operational documentation
• Planning, coordination and professional support during project implementation
• Operation and automation of Oracle systems on x86-based Linux server platforms
• Testing and quality assurance of the developed Puppet modules
• Analysis and resolution of technical errors as part of the automation and migration
• Close coordination with specialist departments and infrastructure teams to implement automation requirements

Technologies used: Puppet 7/8, SLES 15, Oracle 19, Oracle Grid, SVN, Windows Server, Confluence, VS Code, Ruby, Bash, Pass

• Built a Python pipeline that converts lectionary web content into structured daily JSON, applying liturgical-calendar rules for accurate weekday and Sunday coverage.
• Shipped a read-only FastAPI REST API with shared Pydantic models and delivered a Kirundi-first web client for browser and mobile use.
• Owned the data layer and backend architecture, collaborating closely on system architecture and interfaces while automating refreshes with GitHub Actions and validating the ETL with pytest.
• Impact: Created a reliable, API-driven source of truth for daily Bible readings in Kirundi, enabling consistent access to previously unstructured content.

• Partner directly with C-level leadership (CEO, CAIO, CTO) on architecture, OKR strategy, and cross-team roadmap prioritization, translating strategic goals into structured engineering requirements.
• Surfaced and mapped technical debt across the entire organization with C-level leadership and co-defined a prioritized remediation strategy, balancing debt paydown against feature delivery.
• Led code reviews and technical standards across the team, fostering a mentor-first environment with two-way feedback dialogue — pairing on complex pipeline work and unblocking junior engineers on async architecture patterns.
• Re-architected the AI companion's core processing pipeline from synchronous to asynchronous with a queue-based worker architecture, enabling horizontal scalability and cutting upload processing time ~4x (from ~22s to 5–10s) while improving response accuracy.
• Designed an AI-driven document intelligence workflow with automatic multi-document classification, per-document summarization, and relevance guardrails for the patient care journey.
• Built a unified patient memory system (short- and long-term context) bridging the document vault and chatbot into a single bidirectional, context-aware platform.

• Development and maintenance of IT architectures with embedded Linux systems.
• Designing, implementing, and optimizing backend applications and script-based solutions.
• Analyzing and resolving issues, including troubleshooting and user support.
• Developing and implementing security concepts for cloud solutions.
• Administering networks (DHCP, DNS, NTP, VPN).
• Technologies: Linux, PowerShell, Bash, Python, Ansible, Kubernetes, GitLab CI.
• Methods: Kanban.

• Idea, design and initial implementation of a service that aggregates publicly available data to estimate prices for certain types of objects
• Collection of data from different data sources and its normalization. Embedding the data using SentenceTransformer and training gradient boost models
• Implementation of a web service that
• reads arbitrary user text
• extends it if some parts of data are missing
• uses a local LLM model to prepare the data for prediction
• embed the data and call for prediction from the gradient boost model
• uses a LLM model to generate a report for the user request including explanations
• Stack: BigQuery, Vertex AI, Cloud Run (GCP), Python, Terraform, DBT, SentenceTransformer, Qwen
• Minor SEO optimizations
• More to come...

• Designed, developed, and configured scalable data applications aligned with business processes and technical requirements.
• Architected scalable, cost-effective data architectures leveraging Snowflake across AWS, Azure and GCP, integrating dbt for data transformation and modeling.
• Built and maintained robust ETL Data Pipelines, ensuring high data quality for seamless migration and cross-system integration.
• Demonstrated strong expertise in SQL & Python with extensive experience in data modeling, ETL/ELT pipeline development, and streaming data processing; proficient in Git-based version control, CI/CD practices, and testing frameworks, with solid knowledge of data quality, observability, cost optimization, security, and data governance principles.
• Led multiple data migration initiatives from SAP HANA to Snowflake using a modular dbt framework.
• Designed and maintained end-to-end data transformation workflows using dbt on Snowflake, implemented layered data models, optimized performance, and ensured high-quality data delivery for business intelligence and reporting.
• Managed development, QA, and production deployments through structured version control and release management using GitLab.
• Integrated and centralized data from multiple sources including relational databases, flat files, Excel, and large-scale systems into Snowflake.
• Applied strong expertise in Sales, Marketing, HR, and ERP data domains, developing and maintaining relevant KPIs and reporting solutions.
• Collaborated with cross-functional teams to deliver end-to-end data solutions on schedule through proactive issue resolution and effective coordination.
• Administered the Snowflake sandbox environment for Data Engineering division.
• Trained colleagues transitioning into data roles on Snowflake and provided technical guidance and mentorship to junior team members.

• Strategic consulting and implementation of AI-supported automation solutions for service processes (email communication, document handling, review processing, voice agents)
• Technical orchestration using n8n (workflow automation), Claude and ChatGPT (LLMs), as well as custom API integrations into existing enterprise tools
• Measurable customer results: response times reduced from hours to minutes, 8 fewer hours of invoice processing per week, 75% fewer routine calls
• Assessment of regulatory requirements (GDPR, compliance) as part of customer consulting
• Technical Product Ownership (backlog, roadmap, prioritization)
• Formal contracting vehicle for freelance assignments, including 1&1 Telecommunications
• Building & scaling enterprise AI platforms

AI-driven automation of purchasing on a printing company's website, including selecting delivery times, order options, ordering, payment, and uploading print data from the Lumiz Cloud.

• Support for implementing the Pimcore CMS, support assistance, and partner management for the existing application landscape.
• Know-how transfer to the existing application landscape.
• Advising stakeholders on the new implementation.
• Support in data modeling for Pimcore.
• Designing and overseeing data migrations from Salesforce to Pimcore using ESB.
• Creating user stories.
• 3rd level support for business-critical processes.
• Technologies: Salesforce Marketing, Sales, and Service Cloud; Talend ESB; Pimcore; Shopware; ERP system Move; DB2; MySQL; MS Office; MS Visio; Jira; Confluence.

Project content: The use of “Generative Pretrained Transformer” technologies (GPT) will massively change the world of work in the coming years. ITZBund is developing a base service for this, which can be used by its 200 customers. This base service is offered as an on-prem and a cloud variant. Started in 12/23, from 05/24 productive systems (based on MVP) could already be rolled out and operated successfully for several agencies and federal ministries.

Project metrics:

• Budget in 2024 approx. €20M
• approx. 70 people in the core project context
• regular (indirect) contact with approx. 80 people in the wider project environment

My main tasks:

• Overall responsible external project manager
• Project definition phase/project setup and establishment of the project organization
• Strategic and operational project planning, as well as shaping and ongoing adjustments of the project
• Ongoing coordination with project owners and stakeholders in ITZBund
• Ongoing coordination with subproject managers, agile roles and other project staff
• Responsibility for project controlling, quality management, risk management and change management
• Responsibility for providing the base service on on-prem and cloud environments and its continuous development
• Planning and leading several hypercare phases
• Collaboration and ongoing coordination with a partner project of a federal ministry and provision of an MVP
• Coordination with agile teams
• Coordination with operations, release and deployment
• Responsibility for the implementation of the first customer projects
• Responsibility for creating an AI governance
• Ensuring accessibility (BITV)
• Responsibility for setting up a subproject for marketing activities
• Support in building an efficient proposal process
• Stakeholder management

Methodology:

• V-Model XT ITZBund
• Scrum

Tools used:

• Microsoft Office, Skype, MS Project, Confluence, Jira, SharePoint, Miro