AI systems that survive production.
Julian HilzingerFreelance software architect & AI engineer
- 10+
- 20+
Clients and organizations I have worked with
“Outstanding in implementing complex requirements.”
My Services
Three starting points companies hire me for.
focus areacertified
Your legacy system slows down every release
I modernize monolithic legacy systems incrementally into scalable microservice architectures, following the strangler-fig pattern and domain-driven design, without big-bang risk. In a three-year engagement I extracted 20+ modules from an enterprise codebase this way.
Java 21/25Spring Boot 3 / 4Angular 17+PostgreSQLKubernetes / AzureDDD & Strangler FigLegacy modernization in detail →Your AI agents should do real work, not demos
MCP servers, agent orchestration, and the governance layer around them: verification loops check every result, guard-rails in CI/CD stop misbehavior, cost controls cap consumption. That keeps autonomous workflows auditable and EU-AI-Act-compliant.
Claude Code (Anthropic Academy)MCP Server & AgentsSpring AIVerification Loops & EvalsAI Compliance (EU AI Act)CI/CD GuardrailsMCP server development in detail →Your team should ship AI-native without losing quality
Team enablement for agentic software development: I take engineering teams from Level 1 (autocomplete) to Level 4, meaning autonomous, spec-driven agent work with human oversight, and where it is defensible close to Level 5. Secured by prompt contracts, verification loops, and guard-rails in CI/CD.
Team enablement in detail →
Five levels of AI-native development
The model I use to place teams — and the level I work at myself. The jumps to 4 and 5 are an architecture question, not a tooling one.
Autocomplete and chat assistance
Where most teams stand today. Both speed up typing; neither changes the process.
Agentic Single Tasks
An agent works directly in the repository: it reads code, edits files, and runs tests, per task and with human approval of every step.
Autonomous Development with Human Oversight
Agents implement entire features spec-driven: specification → plan → implementation → verification.
Autonomous Agent Teams
Multi-agent systems plan, implement, and verify on their own; the human sets goals and owns the outcomes.
Level 5 in a live client project since 04/2026 — backed by prompt contracts, verification loops and guard-rails in CI/CD.
Selected Projects
Full Stack Engineer AI Native
Software VendorFully AI-native development approach with Claude Code at level 5 — autonomous agent teams, humans set the goals and own the outcome.
Claude CodeAIJavaAWSHerd Management Platform
AgriTech CompanyThree-year engagement, 20+ modules extracted from a monolith, plus MCP server infrastructure for AI agents and process automation.
MCPJava 21/25Spring Boot 3AzureDigital Funding Platform
Public Sector ClientDigital platform for maintaining and analysing nationwide funding data — microservice architecture, project lead and software architecture.
MicroservicesSpring BootAngularPythonFC Bayern Hackdays – Telekom Challenge
1st PlaceFirst place against 1,300+ applicants: an AR prototype for the Microsoft HoloLens, team lead and development within 48 hours.
Microsoft HoloLensC# / UnityARJava
This website is an MCP server
Connect Claude directly to this site and query profile, services, career and coverage area.
https://hilzinger.dev/api/mcpclaude mcp add hilzinger --transport http https://hilzinger.dev/api/mcpclaude.ai: Settings → Connectors → “Add custom connector” → paste the URL
Read-only by design: the server exposes reading tools only, following the same guard-rail principles I build into production agent systems.
Julian Hilzinger
I have been building software for over 10 years, specializing in the modernization of complex legacy systems, cloud-native architectures, and the integration of AI agents. I build the governance layers that let agents do real work without losing track of cost or traceability.
- Fridingen a.d. Donau, Baden-Württemberg
- Remote across the DACH region, on site in Tuttlingen, Sigmaringen and the Zollernalb district
- 10+
- 20+
Career & Certifications
- Head of IT Innovations
App development (Apple, Android, web), AR/VR, machine learning, prototyping of new IT technologies and technical lead of a large-scale project (> 800 person-days).
- M.Sc. Business Analytics
- Senior Software Architect & AI Engineer
Software architecture & AI engineering, cloud-native solutions, technical lead and digital transformation strategy for clients in industry and the public sector.
- Lecturer
Module Mobile Systems and Cloud — teaching iOS, Android, Azure Cloud, software architecture and digitalization.
- B.Sc. Business Informatics
Certifications
- Claude Code in Action
Model Context Protocol: Advanced Topics · Building with the Claude API
- Azure Fundamentals
Azure AI Fundamentals · Azure Data Fundamentals
›Show all certificates (6)
- Professional Scrum Master
Certificate of Completion
- AI Competence Training
EU AI ACT – Compliance & Application
- Digital Disruption
Digital Transformation Strategies
- Data Strategy
Leveraging Data as a Competitive Advantage
- Technology, Strategy and Leadership
Executive program of the German National Academy of Science and Engineering
- Business & Digital Transformation Program
Business Strategy, Entrepreneurship, Marketing & Innovation
Awards
- Philipp-Matthäus-Hahn Award
Best graduate of the M.Sc. Business Analytics program, awarded by the Philipp-Matthäus-Hahn Foundation.
- 1st Place FC Bayern Hackdays
Winner of the Telekom Challenge with AR/VR project. Programming competition with more than 1,300 applicants.
- IDEA Award
Innovative. Digital. Experience. Award for a digital innovation project at Gühring IT.
Get in Touch
Tell me about your project. A first conversation comes with no obligation.
Direct Contact
I look forward to your inquiry and typically respond within 24 hours.
How I work: The AI Coding Levels model →
- Fridingen a.d. Donau, Baden-Württemberg