Working Student - AI Engineer

Mission

Construction is a $13T industry that still runs on PDFs, email chains, and manual cross-referencing. Every major project generates thousands of pages of contracts and commercial documents that nobody has the time to read properly and mistakes cost millions. We're building the intelligence layer that changes that.

What You'll Own

This isn't a "support the real engineers" role. You'll own real parts of the product, ship to production, and see your work used by actual customers, on a flexible schedule that fits your studies.

• AI Pipelines: Build and improve document processing, extraction, and retrieval pipelines. Test new models, optimize prompts, run evaluations.

• Full-Stack Features: Pick up issues across the stack, backend endpoints in FastAPI, frontend components in Next.js, data layer in Supabase.

• Evaluation & Data: Help build the eval infrastructure and datasets that keep our AI reliable. Measure what matters.

• Ship what's needed. We're a small team. New feature today, PDF parser bug tomorrow. You pick up what moves the product forward.

Who We're Looking For

You're studying CS, informatics, or something related at a Munich university and you're already building on the side. Hackathons, side projects, open-source, freelance work. You have a GitHub (or equivalent) that shows you actually enjoy this.

20 hours/week. Munich-based.

Technical

• Solid Python skills, you've written more than university assignments

• Experience with at least one web framework (FastAPI, Django, Express, etc.)

• Frontend basics: React or Next.js preferred

• Interest or experience in LLMs, RAG pipelines, or AI tooling

• Comfortable working in a real codebase: git workflows, PRs, code review

• Bonus: experience with vector databases, LangChain/LangGraph, or document processing

Mindset

• High agency. You figure things out. You Google, read docs, try stuff, then ask smart questions.

• Reliable. You hit your commitments. When you say you'll finish something by Thursday, it's done by Thursday.

• Builder at heart. You're not here to pad your CV. You want to build something real.

What You Get

• Production experience. Your code ships to real users. That's worth more than any university project.

• Grow fast. Work alongside the CTO and founding engineers. Learn how to build AI products for real.

• Competitive working student salary.

• Flexibility. We work around your university schedule.

• Whatever tools you need. Hardware, Claude Code, unlimited AI credits, productivity setup — just ask.

• Team dinners and occassional offsites.

Interview Process

We're thorough but we respect your time.

1. Intro call — Meet a founder. (~30 min)

2. Technical deep dive — We go deep on your experience, how you think about systems, and how you'd approach real problems in our domain. (~1 hr)

3. Take-home — A time-bounded, practical challenge based on our actual work. AI + full-stack, end-to-end.

4. Technical follow-up — Present your take-home, walk us through your decisions, and dig into the trade-offs together.

5. On-site day — Work with the full team from our Munich office. See how we actually build.

6. Offer.