Curiosity, competition, then building.

Grew up in Erfurt, specialized STEM school, HPI since 2024. I build agentic-AI products in small teams and test them against real users.

I grew up in Erfurt, went through a specialized STEM school and the federal computer-science competition, and moved to Potsdam for HPI in 2024. I work in focused sprints and use AI coding agents heavily, and say so: the architecture decisions, the test strategy and the review are mine.

Potsdam, 2026

Four steps, one direction.

Curiosity
Math olympiads from sixth grade, the entrance exam for a specialized STEM school in Erfurt, the federal computer-science competition.
Competition
Thirteen years of karate. A CNN written from scratch won the Thuringian round of Jugend forscht and a special prize at the national final (2024).
Building
A winning team at the first Bundesliga Hackathon (2025). Then production code: Founding Engineer at Kobe AI, and a voice agent for 100+ salons at MitJulia (formerly Friseurtelefon).
Impact
Medical volunteer in Red Cross civil protection since October 2024; a workshop day for 87 eleventh-graders with my scholarship foundation. Skills only count once they work outside your own CV.

Three habits you can check in the repositories.

Evidence before code

I reproduce a problem on a real transcript and check every configuration before I change anything.

3,200 / 0

comparisons on 400 generated catalogs against an independent re-implementation, 0 deviations

Focused sprints

Short, intense build phases with a clear goal, then review and clean-up.

32 in 5 days

commits on the takeøff website; 477 at Kobe in October 2026

Agents, openly

I use AI coding agents heavily and say so. The architecture decisions, the test strategy and the review are mine.

projects with written agent contracts (AGENTS.md, CLAUDE.md)

What I build with.

One line and one number per area. The evidence is one click away.

AI agents and evals

LLM agents with tools, MCP and voice, plus the evals that keep them honest.

267 eval cases, grown from 67 (MitJulia, 2026)

Evidence

A production voice agent for 100+ salons at MitJulia with an eval simulator (67 → 267 atomic cases, GPT-4o-mini as the caller); a six-stage agent pipeline on the Claude Agent SDK at Kobe, co-developed, with a rubric review agent that scores reports on five dimensions (0–3); extended the MCP server of the Kobe backend; the OpenAI Agents SDK and Realtime API for Voya; a talk on AI hallucination (Biases & Mishaps, 1.3).

Full-stack TypeScript

Production code in two startups: web, backend and an Electron desktop client.

434 + 477 commits at MitJulia and Kobe, 2026

Evidence

434 commits in the MitJulia monorepo (Aug – Nov 2026) and 477 commits at Kobe in October 2026: Next.js and React, Node with Hono, Electron, Vite.

Python and machine learning

From a CNN written from scratch in NumPy to PyTorch benchmarks and YOLOv8.

7 architectures benchmarked in PyTorch (PneuNet)

Evidence

A CNN with its own backpropagation in NumPy (2023), seven architectures benchmarked in PyTorch, YOLOv8 segmentation on a CPU, and now the GorillaScout bachelor's project (detection, tracking and re-identification of wild gorillas).

Cloud and data

Serverless on AWS and Cloudflare, Postgres with Drizzle, Supabase, SQLite.

100+ Lambda functions in one AWS backend (MitJulia)

Evidence

An AWS SAM backend with over 100 Lambda functions and 9 DynamoDB tables; Cloudflare Workers in four projects, some with Durable Objects; Postgres and Supabase across several projects, with Drizzle and row-level security at Kobe; SQL, Database Systems I graded 1.7.

Engineering practice

Architecture, tests, CI and code review, with AI coding agents under clear contracts.

1.0 in both Software Architecture and Software Engineering

Evidence

Software Architecture and Software Engineering both graded 1.0 (exam, system demo, code review); design patterns, ADRs and Scrum in the team projects of both courses; CI in a seven-year-old codebase with coverage raised from 84 to 95 percent (team); agent contracts (AGENTS.md, CLAUDE.md) in 8+ projects.

Processes and requirements

BPMN 2.0, interviews and requirements, the enterprise view on software.

3 BPMN projects, from interviews to process models

Evidence

BPMN 2.0 in three projects; for the ESN Event Hub five stakeholder interviews that surfaced 15 pain points; Enterprise Applications 1.3; Global Design Thinking Workshop at the HPI d-school 1.0.