technical Part 2
Agentic Engineering Without Chaos
Coding agents make output cheap. Production teams still need proof, scoped changes, dependency hygiene, review discipline, and rollback paths.
March 30, 2026
aisoftware-engineeringcoding-agents +2
Senior Data & AI Platform Architect
Production AI on brownfield enterprise data
I design the data platforms enterprise AI actually runs on: dimensional and Data Vault modeling, lakehouse and warehouse architecture, streaming and batch pipelines. On top of that foundation I build the AI layer, from retrieval with source attribution to agentic workflow patterns, with the evaluation criteria and multi-tenant runtimes that keep it observable.
Hands-on technical leadership | M.Sc. RWTH Aachen | DACH | Europe | Remote
About Me
My strongest fit is senior hands-on work where data architecture and AI meet, combining architecture ownership with technical leadership, mentoring, and cross-team enablement. Since 2020, I have modeled and shipped enterprise data platforms in insurance, IoT, and AI-native products. Before that, my foundation was embedded systems, high-performance computing, and production software engineering.
My engineering path started early: in high school, I designed the electronic control system for a patented fire simulation device, from PCB design to Windows GUI. That full-stack mindset still guides my work today. At HDI, I modeled analytics domains against an enterprise insurance warehouse using Kimball and Data Vault 2.0 patterns. At EdgeIQ, as Senior Data Architect, I owned the tenant-facing data model for a multi-tenant IoT platform: device, event, and time-series domains, with a dbt transformation layer that kept analytics contracts stable while the underlying schema moved. The same platform ran a workflow runtime and Kubernetes provisioning controllers, so I learned early that a data model is only as good as the runtime that has to honour it. With an M.Sc. from RWTH Aachen and a background in probabilistic modeling, I build systems that handle uncertainty and hold up in production.
What sets me apart: I care about operating boundaries as much as features. Most AI projects fail on the data layer, not the model. I have spent as much time on modeling standards, lineage, and transformation contracts as on retrieval, agentic workflow patterns, evaluation criteria, and the human review boundaries that decide when a system should act and when it should ask. Teams need to understand not only what a system does, but how it fails and how to recover.
I am primarily looking for full-time senior data and AI platform roles where I can own the data platform end to end and provide hands-on technical leadership across modeling, architecture, pipelines, evaluation, infrastructure, and operational handover.
Based in Germany. German native, English fluent. Open to DACH, European, and compatible global remote roles, with consulting or advisory work as a secondary path when there is a strong technical fit.
Experience & Credentials
A career arc from embedded and HPC systems to enterprise AI, data platforms, and production workflow infrastructure.
Work
Projects
Education
2025
2025 - Present
AI Engineer & Architecture Consultant
Independent • Aachen, Germany
- • Deliver architecture advisory for enterprise data platform, AI/ML, and IoT initiatives, translating established workflows into target architectures and rollout plans
- • Advise on lakehouse and warehouse target architectures, including modeling standards, transformation layers, and migration sequencing away from legacy warehouses
- • Design and facilitate enterprise AI workshops that turn LLM and retrieval use cases into evaluation criteria, guardrail requirements, and measurable adoption plans
2023 - 2025
Senior Data Architect
EdgeIQ • Remote (US)
- • Owned architecture and hands-on delivery for a multi-tenant enterprise IoT workflow platform, reducing customer onboarding time by 70% through reusable workflow and integration patterns across 100+ custom Node-RED nodes
- • Owned the tenant-facing data model across device, event, and time-series domains, using dimensional modeling and a dbt transformation layer to keep analytics contracts stable while the underlying IoT schema evolved
- • Designed Generic Timeseries API (Go/TimescaleDB), replacing 5+ specific endpoints and cutting dashboard delivery from weeks to hours
2023 - Present
Founder & Lead Developer (Side Project)
Zeitgaist • Aachen, Germany
- • Started immediately after ChatGPT's first public launch as a Perplexity-like real-time RAG answer engine while mainstream assistants were still knowledge-cutoff-limited
- • Built dense retrieval with Sentence Transformers and cross-encoder reranking across 6 social platforms
- • Implemented cross-lingual search supporting 20+ languages with automatic query translation
2021 - 2024
Co-founder & Lead Developer (Startup)
Foretale • Aachen, Germany
- • Co-founded no-code trading platform with visual workflow automation for cryptocurrency strategies
- • Built distributed ML backend (FastAPI/Ray/PyTorch) for real-time sentiment analysis and OCR
- • Created custom Node-RED fork with 25+ trading nodes and Svelte-based UI components
2020 - 2022
Data Scientist & Data Engineer
HDI (Talanx Group) • Cologne, Germany
- • Led development of a German-language NLP pipeline automating >95% of bank-data change email requests and saving an estimated 200+ analyst hours/month
- • Integrated Planet AI handwriting recognition and validation workflows processing 15,000+ forms/month, reducing manual transcription in insurance document operations
- • Modeled analytics domains against HDI's enterprise Data Warehouse using Kimball dimensional and Data Vault 2.0 patterns, giving downstream data science teams a consistent consumption layer
2019 - 2022
Consultant & Developer (part-time)
TurnDigital GbR -- IT Consulting • Aachen, Germany
- • Delivered ML forecasting and AWS infrastructure modernization for SMB clients, contributing to reported reductions of 15% in inventory costs and 30% in cloud costs
2018 - 2020
Master of Science in Electrical Engineering, IT, and Computer Engineering
RWTH Aachen University • Aachen, Germany
- • Focus on Machine Learning, Embedded Systems, and High Performance Computing
- • Developed a hybrid EA+RL framework combining behavior trees for instinctive behavior with Q-learning, PPO, and DQN for learned behavior
- • Thesis: "Evolving Behavior Trees for Reinforcement Learning on Medical Databases" (Grade: 1.0, best possible German grade)
2017 - 2018
Software Engineering Intern
Silexica GmbH -- later acquired by Xilinx, now AMD • Cologne, Germany
- • Built Yocto/BitBake integration for SLX Tools across 6 target architectures, enabling analysis of embedded Linux applications for automatic parallelization
- • Analyzed an AUTOSAR Adaptive autonomous-driving workload and identified an analyzer-estimated 8x theoretical speedup ceiling on an 8-core platform
- • Supported 6 processor architectures (ARM, MIPS, PowerPC, x86) for cross-platform analysis
2014 - 2017
Working Student -- R&D
Lumileds Germany GmbH (formerly Philips) • Aachen, Germany
- • Conducted hardware measurements and stress testing for automotive LED products and developed firmware optimizations
2013 - 2018
Bachelor of Science in Electrical Engineering, IT, and Computer Engineering
RWTH Aachen University • Aachen, Germany
- • Focus on Computer Engineering, High Performance Computing, and Digital Systems
- • Implemented an SHM-LXC pscom plugin for Parastation MPI, enabling shared-memory communication between containerized HPC nodes
- • Thesis: "Implementation of a Light-weight Software Layer for Inter-process Communication" (Grade: 1.3, second-best possible German grade)
Summer 2007
Engineering Intern
Halfkann + Kirchner • Germany
- • Designed electronic control system for patented fire simulation device (DE102008011567B4)
- • Built custom PCB and programmed ATmega microcontroller in C/Assembler
- • Created Windows GUI enabling engineers to draw custom fire progression curves
Featured Projects
Selected engineering work that shows platform ownership, production constraints, and applied AI/data systems beyond prototypes.
Enterprise IoT Platform
Multi-Tenant Workflow Automation Infrastructure
EdgeIQ professional case study: enterprise platform for IoT workflow automation consisting of an extended Node-RED engine, two Kubernetes controllers for multi-tenant provisioning, and an API gateway with observability instrumentation.
Reduced customer onboarding time by 70% and eliminated an estimated 40+ hours/month of manual DevOps while the architecture was designed for 1,000+ isolated workflow instances.
ReactGoTypeScriptTimescaleDBAWS +5
Zeitgaist
Cross-Lingual Social Intelligence
Early post-ChatGPT dual-product AI platform combining a conversational retrieval chatbot and social analytics dashboard. Both share a unified Python/FastAPI backend with two-stage retrieval, social-media indexing, and multi-language NLP.
Synthesizes current insights from 6 platforms in seconds vs hours of manual monitoring, with cross-lingual search and filterable source context.
Real-Time RAGRetrieval SystemsLLMNLPPython +3
ArchiveForetale
No-Code Crypto Trading & Real-Time NLP Platform
No-code crypto trading platform combining real-time NLP inference, multi-source data aggregation, and visual workflow automation.
Platform processed 100K+ daily source events across 7+ sources with ML-powered sentiment analysis, OCR extraction, and visual workflow automation.
PythonPyTorchNLPKafkaStreaming +3
Selected Writing
Practical notes on production AI, agent governance, career risk, and the engineering judgment behind systems that need to work after the demo.
guide Part 1
From AI Prototypes to Governed Agents
AI prototypes are easy now. Production agents still need architecture, policy boundaries, verification, observability, and accountable rollout.
March 29, 2026
aienterprise-architectureagents +2
Skills & Expertise
Production-focused capabilities tied to the roles and case studies on this site, not a generic technology inventory.
Data Modeling & Warehousing
Data Platforms
Applied AI
Agentic & Workflow Systems
ML & NLP
Platform & Infrastructure
Technical Leadership
Languages
German (Native) English (Fluent)