CTO / Head of Engineering
Ship reliable systems. Even the AI ones.
I've spent 15 years stabilizing platforms where downtime costs money. Now I apply the same discipline to AI systems where hallucinations cost more than downtime — maritime decision-support, legal document retrieval, critical infrastructure. Ownership, metrics, reliability over heroics.
Best fit: B2B SaaS scaleups navigating growth — and teams shipping AI into production where accuracy, citations, and evaluation matter.
Frankfurt, DE
CTO / Engineering Leader • Platforms & AI
Stability and performance as systems scale under real load.
RAG, evals, and reliability practices for AI where accuracy is non-negotiable.
Clear ownership, delivery cadence, and accountability without bureaucracy.
Case Studies
Selected engagements in modernization, reliability, and platform scale.
Building RAG for German Legal Documents: When Hallucination Isn't an Option
RAG system for German social law that helps the Balkan diaspora navigate Jobcenter bureaucracy — with forced citations, bilingual retrieval, and an evaluation harness that actually catches failures.
Role: Founder & Engineer • Scope: RAG architecture, corpus ingestion, evaluation harness, production system
Citation-grounded answers • 50+ golden eval set
Operating Model Turnaround: From Chaos to Predictable Delivery
A pragmatic playbook to stabilize delivery, clarify ownership, and build a sustainable cadence.
Role: Engineering Lead / Head of Engineering • Scope: operating model, delivery systems, reliability practices
Chaos → predictable delivery
Microservices Modernization: From Monolith to Observable Platform
Shortened release cycles and reduced incident impact through microservices migration and SLO-driven reliability
Role: System Architect • Scope: platform modernization + observability + reliability
Release cycle days → hours + SLO-driven ops
How I Lead Engineering
I build engineering systems that scale: ownership, reliability, and delivery cadence-so leadership can plan, product can commit, and customers feel stability.
Non-negotiables: ownership over activity, metrics over opinions, calm operations over heroics.
Systems
Architecture ownership
Define target architecture and decision-making (ADRs) so teams move fast without rework.
Reliability as a function
Implement SLIs/SLOs, error budgets, and incident response to cut critical incidents and improve resilience.
Delivery system
Standardize CI/CD and infrastructure to make releases predictable, repeatable, and fast.
People & Alignment
Team scaling
Hire, onboard, and mentor engineers; create clear roles, ownership, and growth paths.
Cross-functional alignment
Align engineering, product, and stakeholders on priorities, trade-offs, and execution cadence.
Tech focus
I use technology to produce outcomes: predictable releases, stable operations, and faster iteration.
Stack
- TypeScript
- React/Next.js
- Node/Nest.js
- GraphQL & REST
- AWS · Terraform · Docker
Practices
- System design & ADRs
- SLIs/SLOs & incident response
- CI/CD & release engineering
- Observability & performance
- Team enablement & standards
AI Engineering
- Python, FastAPI
- RAG architectures (ChromaDB, FAISS, pgvector)
- OpenAI, Anthropic, local models (Ollama)
- Embedding models for bilingual retrieval
- Eval harnesses (RAGAS, custom) with golden datasets
- Hallucination guardrails & citation-forced generation