Software Engineer - AI

tl;dr

- After 14 years in construction tech, Lea & Jonas are building the AI foundation for the construction industry

- 6 of the 20 largest construction companies in the German-speaking region already rely on Kuro every day, representing over €40bn in combined annual construction volume

- Construction has some of the most complex, unstructured data you can throw at an LLM. At Kuro, you can tackle some of the hardest problems in applied AI every day

- Curious about the bigger engineering challenge? Explore the vision and open problems at kuro.build

Lea and Jonas scaled two of Europe's leading construction tech companies - Capmo and alcemy - and saw firsthand the challenges holding the industry back. Now they're tackling the root cause: the 50% of construction work still lost to manual data handling.

Kuro is building the AI foundation for construction. We're reimagining how construction professionals get work done and make decisions by leveraging AI to augment back-office workflows and make core data accessible. We are not pursuing marginal improvements, but a step change for construction.

After one year on the market, leading construction enterprises with a combined annual construction volume of >€40 billion use Kuro every day to automate workflows and make faster, better decisions. Backed by an €10 million seed round, we already process more than 1 million pages every month and expect that volume to grow 10x over the next six months.

We are 15 people based in Berlin. You will join a group of technical ex-founders and builders who are ambitious and kind.

Learn more: Join Kuro - Berlin

Set the technical direction

• Own the architecture decisions for the platform, from document ingestion to the chat UI
• Write and review RFCs. The technical roadmap for the next two to three quarters is yours.
• Make the build-or-buy decisions: which models we use, and which retrieval and orchestration stack we build on.
• Turn a vague customer request (“show me where the bid deviates from the BoQ”) into a scoped plan with the risks named.

Current & Past projects

• Project & document versioning guaranteeing data lineage in construction projects
• German tokenizer for construction-specific search
• Document pipeline ingesting 10,000s of PDFs per day
• Native BIM/DWG file support: ingesting and processing 3D models
• Design the ontology v1 + graph schema: core construction entities, evidence links, and per-customer extension model
• Build out our workflow harness to run agentic workflows for customers

Current Tech Stack

It is still day 0 for Kuro. Therefore, we are highly pragmatic with our tool choices. We believe in keeping it simple and moving quickly. You significantly help shape our tech stack decisions.

• Web-App: Typescript
• Database / Vector DB and File Storage: AWS RDS / Trubopuffer / AWS S3
• Backend: Fastify API + Prisma ORM
• Workflow Orchestrator: Prefect (Python)
• Hosting: AWS Elastic Beanstalk
• AI: Azure / OpenAI, Gemini, Cohere, AWS
• Obsv., Eval. & Tracking: Langfuse, Datadog

This is the perfect role for an experienced engineer who wants to join an early stage company that builds a high impact applied AI product

• Bring 6+ years of experience as a Staff (full-stack) software engineer or Technical Lead, in a fast-paced environment
• Have proven experience delivering production-grade applied AI features to customers
• Take full ownership of solving customer problems by designing and implementing AI features
• Thrive in a small, accountable team with a high degree of ownership and a drive to make an impact
• Communicate fluently in both spoken and written English
• Enjoy working onsite with the team at our office in Factory Berlin Mitte every day
• You’ve started a company before or worked at a very early stage startup
• You built side projects in the past - we’re excited to hear about these!
• German-speaking (definitely not a must, we’re fully international)

Why Kuro

You’ll join at a point when customer demand is proven, but our product and platform are still yours to shape. You’ll own customer-facing features end to end while building the foundations beneath them, from ingestion pipelines and workflow infrastructure to our construction ontology and project graph.

As Kuro grows, you can grow with it, whether as a leading individual contributor, technical leader or people manager.

The Process

• Talent Acquisition Call – Intro, motivation, logistics & fit (30 min)
• Impact Interview – Deep dive into your experience, ownership & impact (60 min)
• On-site Day
• System Design – Designing under ambiguity & LLM craft (45 min)
• AI-Native Coding – Hands-on coding with AI (45 min)
• Final Culture Interview (approx. 60 min)
• Reference calls
• Decision

• Mentor engineers: Review their designs and their code.
• Define the engineering standards. Find what slows the team down, in tooling or in the CI/CD pipeline, and fix it.
• Interview and hire engineers.
• You have no direct reports. You change decisions in product and in other teams with a written argument.

Build and own end-to-end (AI) features

• Design and implement new features to solve a specific user problem, such as document versioning or our agentic Chat.
• From concept to DB schema, to optimizing LLMs, to UI. Own the full development lifecycle of customer-facing features.
• Manage evaluations and scoring, and perform error analysis on new and shipped AI features.

Build the platform that abstracts workflow building

• Contribute to the workflow harness, decision-trace standard, and eval tooling so a new use case ships in ~1 month
• Build reusable human review & approval surfaces where trust in AI output is earned

Work on the construction ontology & project graph

• Help model and evolve canonical entities of our customers
• Contribute to entity resolution across sources: recognizing the same requirement, position, or price across BoQs, contracts, drawings, and bids
• Build features so answers are evidence-linked and auditable, and decisions flow back into the graph

Contribute to scalable data pipelines & integrations

• Extend our multi-modal ingestion of unstructured documents - PDFs, scans, drawings, and 3D models - orchestrated and cost-efficient at scale
• Build read/write integrations with customer systems (document management, ERP/AVA), so workflows complete work end-to-end