Founding AI Engineer

The construction industry loses $1.6 trillion annually to inefficiencies not because people are careless but because critical knowledge is trapped in PDFs transcripts and scattered systems. Every new project starts from scratch.

Were building the opposite: an AI co-worker that extends the Projektsteuerer (the person who runs complex construction projects) while every project makes our system measurably better. The moat isnt the model its the compounding project memory no competitor can replicate.

Pre-seed led by Realyze Ventures LPs include Zech and other major European construction -investors: D11Z (the family office behind Aleph Alpha) and the CDTM Venture Fund (backed by 300 CDTM alumni including founders of Personio Alasco and the Technical Director of DeepMind).

Our software is running today on a major autobahn construction program and an S-Bahn transit program multi-year timelines hundreds of thousands of pages of specs protocols and communications. Real consequences when we get it wrong.

Tasks

What youd actually work on

• **1. Agent harness engineering for construction documents
  **One summary doesnt fit all. Structural risk in an RFI means something different than in a cost review which means something different in a schedule reconciliation. We build multi-agent harnesses specialized extraction reasoning evaluation stages that route 400-page tender documents and protocol archives to the right pipeline with the right context.
  If youve read Anthropics or LangChains writing on agent harnesses and thought yes thats the hard part of shipping production agents thats this job.

• **2. Project memory as a compounding moat
  **We started with meeting transcripts. Were building a decision graph that grows with every project tracking not just what was decided but why by whom against which alternatives and with what outcome. That graph feeds the next project. Every closed workflow makes the next one faster.
  This is the operational-continuity layer no ConTech player is building. We want someone who gets excited that the hard part here is not retrieval its deciding what signal to keep.

• **3. Context compression for 5 year projects
  **What should the system remember Forget Surface at which decision point Theres no clean top-k answer when a project spans 5 years and touches 50 stakeholders. This is an open research problem were solving in production and wed rather hire someone who reads papers than someone who installs libraries.

Stack: TypeScript Vercel Supabase (Postgres pgvector) LangChain Vercel AI SDK LangFuse shadcn/ui. 500/month AI tooling budget per engineer Claude Code Cursor background agents experimentation with frontier models. No legacy. Greenfield.

Requirements

Who were looking for

• Product sense: you reason from user pain solution measurable outcome. You can talk to non-technical customers and understand their workflows.
• Velocity craft: prototype fast measure everything iterate on real feedback. But you care about reliability because the downside of wrong is real in construction.
• Comfort with the unknown: many of these problems dont have Stack Overflow answers. You read papers prototype and compare approaches.
• Bonus: strong open-source work previous early-employee startup experience domain depth in document understanding or agent systems or shipped systems that replaced hours of human labor.
• Level is opportunistic: Weve seen brilliant new grads outperform staff engineers and vice versa. If youre exceptional well find the right scope.
• Language: We work in English. German is nice-to-have for customer conversations but not required we have native speakers for that.

Benefits

As one of our first hires youll do more than contribute youll help shape how Alago works: our culture systems and growth strategy. Youll work directly with the founders gain exposure to every function and ship projects that have immediate impact.

• 10 Learning Curve. Work with cutting-edge AI to tackle real-world challenges every day
• Work directly with the founders. Youll own critical parts of alago end-to-end laying the technical foundation while balancing rapid iteration customer value and long-term scalability.
• Hybrid: A vibrant in-office culture in our central Munich office. 3 days per week in our central Munich office flexible otherwise.
• Meaningful equity stake: 0.5% 1.5% (4-year vest 1.5-year cliff)
• Your needs and well-being matter to us. Youll get access to sponsored EGYM Wellpass to find inner peace at yoga or kill it at HIIT workouts.

Were building for scale but right now its still early. That means lots of autonomy tight feedback loops and the freedom to grow into whatever role suits your strengths whether thats become top individual contributor or stepping into leadership roles like VP Engineering.

1. Three stages. No five-round loops.
   90-minute first call with one of our engineers and then if you impress us you will speak to one of the co-founders directly.
2. Onsite case study in Munich. We send you the materials in advance plan on about 4 hours of preparation. You come to our office and we work through it together. This is where we see how you think debug and ship under real conditions.
3. Offer. Decision within 24 hours of the case study. Offer out within 48 hours.