Grew up in Erfurt, specialized STEM school, HPI since 2024. I build agentic-AI products in small teams and test them against real users.
Before I change a product I reproduce the problem on a real transcript and sweep every configuration in the fleet. Defaults stay conservative, per-customer opt-in rather than global switches. Every hand-over names what I did, what I did not do, and what could go wrong, written so that a non-engineer can follow it.
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.
Path
Four steps, one direction.
01
Curiosity
Math olympiads from sixth grade, the entrance exam for a specialized STEM school in Erfurt, the federal computer-science competition.
02
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).
KC
03
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).
MJ
04
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.
How I work
Three habits you can check in the repositories.
3,200 / 0comparisons on 400 generated catalogs against an independent re-implementation, 0 deviations
Evidence before code
I reproduce a problem on a real transcript and check every configuration before I change anything.
32 in 5 dayscommits on the takeøff website; 477 at Kobe in October 2026
Focused sprints
Short, intense build phases with a clear goal, then review and clean-up.
8+projects with written agent contracts (AGENTS.md, CLAUDE.md)
Agents, openly
I use AI coding agents heavily and say so. The architecture decisions, the test strategy and the review are mine.
Skills
What I build with.
One line and one number per area. The evidence is one click away.
AI agents and evals
267eval cases, grown from 67 (MitJulia, 2026)
LLM agents with tools, MCP and voice, plus the evals that keep them honest.
Claude Agent SDK
OpenAI Agents SDK
MCP
ElevenLabs
Twilio
Evidence
Voice agent in production at MitJulia, 100+ salons (Nov 2026); a simulator lets GPT-4o-mini play the caller across 267 atomic test cases, grown from 67.
Kobe: co-developed a six-stage agent pipeline on the Claude Agent SDK (about 20k lines of Python), including a rubric review agent that scores reports on five dimensions (0–3), and extended the MCP server our CTO had set up (27 of 89 commits).
Before one product change I checked a booking gate against an independent re-implementation: 400 generated catalogs, 3,200 comparisons, 0 deviations.
Talk on AI hallucination in the course Biases & Mishaps (1.3).
Full-stack TypeScript
434 + 477commits at MitJulia and Kobe, 2026
Production code in two startups: web, backend and an Electron desktop client.
TypeScript
React
Next.js
Node.js
Hono
Electron
Evidence
MitJulia monorepo: 434 commits between August and November 2026.
Kobe: 477 commits in October 2026 across the backend, the Electron desktop client and the pitch deck.
takeøff website: bilingual, 32 of 33 commits in five days, live on Vercel.
Python and machine learning
7architectures benchmarked in PyTorch (PneuNet)
From a CNN written from scratch in NumPy to PyTorch benchmarks and YOLOv8.
Python
PyTorch
NumPy
OpenCV
YOLOv8
FastAPI
Evidence
PneuNet: a CNN with its own backpropagation in NumPy, then seven architectures in PyTorch; Jugend forscht 2024, Thuringian state winner.
Real-time trash segmentation with YOLOv8 on a CPU, winning team at the Siemens × AWS hackathon 2025.
Now: GorillaScout, a bachelor's project (team of eight) on detecting, tracking and re-identifying wild gorillas.
Cloud and data
100+Lambda functions in one AWS backend (MitJulia)
Serverless on AWS and Cloudflare, Postgres with Drizzle, Supabase, SQLite.
AWS
Cloudflare Workers
PostgreSQL
SQL
Drizzle
Supabase
Vercel
Evidence
MitJulia: an AWS SAM backend with over 100 Lambda functions, 9 DynamoDB tables and S3.
Cloudflare Workers in four projects, some with Durable Objects; Postgres and Supabase across several projects, with Drizzle and row-level security at Kobe.
Database Systems I graded 1.7.
Engineering practice
1.0in both Software Architecture and Software Engineering
Architecture, tests, CI and code review, with AI coding agents under clear contracts.
Git
GitHub Actions
Vitest
Playwright
Claude Code
Evidence
Software Architecture and Software Engineering both 1.0: exam, system demo and code review.
Set up CI in a seven-year-old codebase; the team raised test coverage from 84 to 95 %.
Agentic workflow: AGENTS.md and CLAUDE.md contracts in 8+ projects, spec → ADR → code; 50+ parallel agent worktrees at the Voya hackathon.
Design patterns, ADRs and Scrum in the SWA/SWT team projects.
Processes and requirements
3BPMN projects, from interviews to process models
BPMN 2.0, interviews and requirements, the enterprise view on software.
BPMN 2.0
Requirements engineering
Design thinking
Evidence
BPMN 2.0 in three projects: Modeling (1.3), ESN Event Hub (1.3), one ongoing.
ESN Event Hub: five stakeholder interviews, 15 pain points.
Enterprise Applications 1.3; Global Design Thinking Workshop at the HPI d-school 1.0.
Also: Kotlin and Jetpack Compose (a 26k-line Android app), Flutter, React Native with Expo, C and C++, Smalltalk, Bash and Linux.
Education
HPI Potsdam, and a STEM school in Erfurt before that.
HPI
Oct 2024 – 2028 (expected) · Potsdam
B.Sc. IT-Systems Engineering
Hasso Plattner Institute, University of Potsdam
GPA 1.4 on the German scale (1.0 is best), 108 ECTS, all exams passed at the first attempt; top grade 1.0 in both Software Architecture and Software Engineering. Specializations: Operating Systems & Information Systems Technology; Software Architecture & Modeling Technology. An exchange semester planned for winter 2027/28 extends the degree to 2028.
GPA 1.4 (1.0 = best)
108 ECTS
1.0 in Software Architecture and Software Engineering
ASG
2020 – 2024 · Erfurt
Abitur, specialized STEM track
Albert-Schweitzer-Gymnasium Erfurt
Abitur 1.4 with advanced courses in English, mathematics, physics and computer science; MINT-EC certificate with distinction. Admission by written and oral entrance exam.
Abitur 1.4
MINT-EC certificate with distinction
Languages
Four languages, two of them for work.
Germannative
Englishfluent (C1)
SpanishB1
Frenchbasic (A1–A2, UNIcert I)
CEFR levels (A1 to C2). English C1 without a certificate; French UNIcert I.
