§ 02

WORK

Kibo AI Nov 2025 – Present
AI Solutions Engineer Nürnberg, DE
  • I build LLM-powered production systems end-to-end — from API integration and prompt engineering to error handling and deployment
  • I prototype LLM integrations for clients, moving from rough proof-of-concept to deployed internal tools
  • I benchmark new models and frameworks against real use cases, not just leaderboard scores
// stack Python Anthropic API Docker
Freelance Jan 2018 – Present
ML & AI Engineer Remote
  • I build end-to-end ML pipelines: data cleaning, feature engineering, model training, deployment
  • I work directly with clients — no account managers, no translation layers. Just me, the data, and the problem
  • Recent work: demand forecasting for a retailer, document classification for a legal team, LLM-powered text extraction from PDFs
// stack Python Pandas Scikit-learn TensorFlow OpenAI APIs SQL Docker
§ 03

PROJECTS

Omni-Pi ↗ Independent

A batteries-included Pi package that interviews the user, documents the spec, and implements work in bounded slices. Built for Node.js 22+.

TypeScript Node.js CLI agent workflows CI
Predictive Maintenance Dashboard University

A dashboard that predicts machine failures before they happen. I trained a Random Forest on sensor data, built the data pipeline, and created a web interface that shows which machines need attention and why. The goal was simple: prevent downtime, not just report it.

Python Pandas Scikit-learn NumPy Matplotlib
§ 04

SKILLS

// AI & ML
LLM system design Prompt engineering OpenAI APIs Anthropic API TensorFlow Scikit-learn
// Languages
Python TypeScript Rust Go Java C Lua
// Infrastructure
Docker PostgreSQL Linux Git
Microsoft Certified: Azure AI Fundamentals (AI-900)
Anthropic API Certification
§ 05

ABOUT

I started freelancing in 2018 because I wanted to work on real problems with real data. Since then I've built everything from demand forecasting models to LLM-powered document processors. I work directly with clients — no middle layers — which means I have to understand the actual business problem, not just the technical spec.

In 2025 I finished my CS degree at Lancaster University Leipzig (first class). My thesis compared DQN and MCTS agents on 3D Tic-Tac-Toe — essentially, I got to spend six months making AIs play a complicated version of a children's game, and they paid me a degree for it. Now I'm at Kibo AI, figuring out how to make LLMs actually useful and reliable in production environments.

Outside of work I'm usually building physical things: a Raspberry Pi running my home automation, an Arduino project that may or may not be a mistake, or something that involves soldering iron burns. I also bike and lift heavy objects repeatedly.

// languages German (Native) · Romanian (Native) · English (C2)