Founding Full-Stack 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
Technical Direction: Work with the CTO to define architecture, make build-vs-buy calls, and set the engineering standards that every future hire inherits. Your decisions become the foundation.
Core Platform: Own the FastAPI / Supabase stack end-to-end — schemas, ingestion pipelines, auth, and the processing layer that turns messy construction documents into structured, actionable data.
AI System: Design and build the multi-agent system powering bid comparison, clause extraction, risk detection, and knowledge graph sync. Decide how agents collaborate, fail, recover, and improve.
Evaluation Infrastructure: Define the evals that tell us whether the system actually works — accuracy, recall, failure modes, cost. Build the tooling that makes the team faster, not just the product better.
Product: Build the Next.js front-end that contract managers trust enough to base million-euro award decisions on. Not a chatbot — a structured workspace.
Production & Scale: Deploy, monitor, keep it running. CI/CD, observability, incident response — the production discipline that earns enterprise trust and keeps pilot customers coming back.
Team Foundation: Help shape hiring decisions, define what "good" looks like technically, and build the engineering culture from the ground up.
Who We're Looking For
Not a senior engineer looking for a comfortable seat at an early-stage company. Not someone who needs a roadmap handed to them.
We're looking for someone who builds like a founder — the kind of engineer who sets up eval infrastructure before anyone asks, who redesigns the auth layer on a Saturday because the current one won't survive the next pilot, who talks to customers and comes back with a better architecture in their head.
You'll operate as a technical co-founder in practice. You stand shoulder-to-shoulder with the CTO — not as support, but as a co-builder. You set the engineering bar, and you keep it there.
Munich-based, or ready to relocate.
Technical Skillset
You've built and shipped AI-powered products with LLMs in production — not prototypes, not demos
Strong Python, hands-on FastAPI or equivalent
RAG pipelines: embeddings, vector stores, retrieval strategies — you've done the hard parts
Experience with LangGraph, LangChain, or similar orchestration frameworks
You've defined and run real evals for AI systems — you know vibes-based testing breaks in prod
Software engineering fundamentals that don't need explaining: clean APIs, tests, versioning, security
You think in systems — balance speed with scale, design things that evolve instead of collapse
You've made infrastructure and architecture decisions that stuck — not just followed them
Bonus
Experience with document processing, OCR, or domain-specific extraction pipelines
Familiarity with knowledge graphs (Neo4j) or graph-based data modeling
Background in construction, procurement, or legal tech
You've been a founding or early engineer before and know what that actually means
Commitment & Mindset
High agency. You see a problem, you fix it. You don't flag it in Slack and wait.
Product-obsessed. You think in user outcomes. You've closed your laptop and thought "would I actually use this?"
Comfortable in ambiguity. Requirements are incomplete. Priorities shift. You make progress anyway.
Energized by intensity. We're building fast, in-person, every day. We want people who thrive in that environment.
Benefits
Impact that's real. Construction is one of the largest, least-digitized industries on the planet. We're not optimizing ad clicks.
Whatever tools you need. Hardware, Claude Code, unlimited AI credits, productivity setup — just ask.
Founding-level equity. Competitive comp + meaningful equity that reflects your role as a foundational builder, not just an early employee. You shape the product, the architecture, the culture.
Intensity + recovery. We push hard and enjoy it. Team dinners, EGYM Wellpass, the right balance.
Occasional San Francisco offsite.
About the Interview Process
We're thorough but we respect your time.
Intro call — Meet a founder. (~30 min)
Technical deep dive — We go deep on your experience as an engineer and as a person. How you think about systems, how you make decisions under uncertainty, and how you'd approach real problems in our domain. (~1 hr)
Take-home — A time-bounded, practical challenge based on our actual work. AI + full-stack, end-to-end.
Technical follow-up — Present your take-home, walk us through your decisions, and dig into the trade-offs together.
On-site day — Work with the full team from our Munich office at Sendlinger Tor. See how we actually build.
Offer.