Senior AI/ML & Software Engineer
Brownfield AI, RAG/LLMOps & Platform Architecture
I integrate AI into systems that were not designed for it, from legacy core platforms to modern microservices. Production AI with human-in-the-loop design, systems that know when to act and when to ask.
Platform Architecture | M.Sc. RWTH Aachen | Germany | Global
About Me
With 10+ years building production AI, data, and workflow platforms, I focus on what makes AI succeed in enterprise environments: clear expectations, strong guardrails, and measurable outcomes. The goal is not blind automation, it is reliable decision support that teams can trust. I help companies reach realistic AI maturity on existing codebases with impact they can track.
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 and EdgeIQ, I modernized legacy platforms and integrated AI into business-critical workflows: German NLP automation, handwriting recognition, Node-RED workflow runtimes, Kubernetes controllers, and observable data platforms. 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 focus on measuring impact, not just shipping features. I design confidence-based routing, human approval gates, and KPI frameworks so teams can see quality, speed, and cost impact continuously. From production RAG systems that improved evaluated top-10 retrieval relevance from 72% to 89% to enterprise workflow platforms supporting 1000+ instances, I build AI that knows when to act and when to ask for help.
I enjoy making complex legacy environments AI-ready and enabling teams to operate systems independently after rollout through workshops, technical standards, observability, and rollout plans. I am open to full-time roles, consulting engagements, and advisory work where measurable business impact is the priority.
Based in Germany, available globally. German (native) | English (fluent). Open to full-time roles, consulting engagements, and advisory positions. If you need production AI with measurable outcomes, let's talk.
Featured Projects
Selected work with quantified outcomes across enterprise AI, data platforms, and production delivery.
Zeitgaist
Cross-Lingual Social Intelligence
Early post-ChatGPT dual-product AI platform combining a conversational real-time RAG chatbot and social analytics dashboard. Both share a unified Python/FastAPI backend with production RAG pipeline, 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.
ArchiveForetale
Real-Time NLP & Multi-Source Data Fusion Platform
Production streaming platform combining real-time NLP inference, multi-source data aggregation, and visual workflow automation. Demonstrates enterprise-grade architecture for social intelligence at scale.
Platform processes 100K+ daily data points across 7+ sources with sub-second latency, running 24/7 with ML-powered sentiment analysis and OCR extraction.
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 a secure API gateway - all with comprehensive observability.
Reduced customer onboarding time by 70% and eliminated 40+ hours/month of manual DevOps while supporting 1000+ isolated workflow instances.
Experience & Education
Roles, projects, and academic foundations focused on shipping measurable outcomes in production environments.
AI Engineer & Architecture Consultant
Independent • Aachen, Germany
- • Advise enterprise clients on AI/ML and IoT platform architecture for brownfield workflows
- • Translate existing systems into production-ready automation designs with Node-RED, Kubernetes, observability, and HITL controls
- • Design AI/ML workshops covering LLM integration, RAG, agentic architectures, evaluation, guardrails, and rollout planning
Founder & Lead Developer
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 production RAG pipeline with two-stage retrieval (Sentence Transformers + cross-encoder) serving 6 social platforms
- • Implemented cross-lingual search supporting 20+ languages with automatic query translation
Senior Data Architect
EdgeIQ • Remote (US)
- • Architected enterprise IoT workflow and data platform, reducing customer onboarding time by 70% with 100+ custom enterprise Node-RED nodes and AWS Aurora to TimescaleDB migration
- • Designed Generic Timeseries API (Go/TimescaleDB), replacing 5+ specific endpoints and cutting dashboard delivery from weeks to hours
- • Automated multi-tenant Kubernetes provisioning, eliminating 40+ hours/month of manual DevOps with 1-second reconciliation
Co-founder & Lead Developer
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
Data Scientist & Data Engineer
HDI (Talanx Group) • Cologne, Germany
- • Built German-language NLP pipeline achieving >95% email-processing automation and saving 200+ analyst hours/month
- • Integrated Planet.AI handwriting recognition for straight-through processing of 15,000+ forms/month
- • Built Python/PySpark ETL bridges from HDI's enterprise Data Warehouse and legacy insurance systems into analytics-ready workflows
Consultant & Developer
TurnDigital • Aachen, Germany
- • Delivered ML forecasting for SMB clients, reducing inventory costs by 15%
- • Consulted on IT infrastructure modernization, reducing cloud infrastructure costs by 30%
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)
Software Engineering Intern
Silexica • Cologne, Germany
- • Built Yocto layers enabling SLX Tools to analyze embedded applications for parallelization
- • Demonstrated AUTOSAR Adaptive analysis identifying 8x speedup potential on multi-core platforms
- • Supported 6 processor architectures (ARM, MIPS, PowerPC, x86) for cross-platform analysis
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)
Electronic Control System Developer (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
Skills & Expertise
Production-focused capabilities I use today to design, ship, and operate enterprise AI systems.