Interdisciplinary Project Student (IDP) - AI Engineer

Mission

Preconstruction is the foundation of every project, where the work gets chosen, priced, and put together. But while the projects have grown, the documents multiplied, and the requirements gotten heavier, the way the work gets done looks almost the same as it did decades ago.

We are building Arctis AI to transform how preconstruction works, making the people who run it faster, sharper, and able to take on more than ever before. By partnering with leading construction companies, we are pushing the boundaries of applied AI and unlocking a multiplier for precon teams.

About the Role

We're looking for an IDP student who's interested in startups, likes taking responsibility, and moves fast. You'll own a real feature and ship it to enterprise customers.

What You'll Work On

• Own a feature end-to-end: From scoping the problem to shipping it to enterprise customers who use it the next day.

• AI systems: Build pipelines and agents that process hundreds of pages of dense project documents and turn them into structured, reliable output.

• Hard problems: Work at the intersection of NLP, document intelligence, and domain-specific AI, directly with the founding team.

Who We're Looking For

• Master's student in Informatics at TUM

• You ship: you figure it out, build it, and iterate instead of waiting for specs

• Strong in Python and/or TypeScript. Bonus: experience with LLMs, FastAPI, Next.js, or graph databases

• High agency, low ego: you care about outcomes, not titles

• You like the pace and openness of a startup — priorities shift, and you enjoy that

What You Get

• Direct impact on a product used by real enterprise customers.

• Learn from builders. Work alongside engineers from Palantir, AWS, Snowflake, and SAP, backed by EWOR.

• Whatever tools you need. Your own Claude Code subscription and unlimited AI credits, we invest in your tools.

• A reference and network that matter if you want to start something yourself.

• Office in central Munich (Sendlinger Tor).

Interview Process

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

2. Technical deep dive — Your experience, how you think, how you'd approach problems. (~1 hr)

3. On-site day — Spend a day at our Munich office at Sendlinger Tor: work through a practical case and build alongside the team.

4. Offer.