Software Engineer - AI

About the Role Join a 15-person B2B construction technology startup as a Software Engineer – AI , owning end-to-end AI features that solve real problems for construction professionals. You'll sit within the Product & Engineering team, working across the full stack — from database schema and LLM optimization to UI — while building platform foundations that allow new use cases to ship in roughly a month. What You'll Do Build and own end-to-end AI features from concept through production, including document versioning and agentic chat workflows. Design and implement features across the full development lifecycle: database schema, LLM tuning, evaluation, and UI. Manage evaluations, scoring, and error analysis on new and shipped AI features to ensure consistent quality. Contribute to the workflow harness, decision-trace standard, and evaluation tooling that accelerates shipping new use cases. Build reusable human review and approval surfaces that establish trust in AI output. Model and evolve a construction ontology and project graph, including entity resolution across documents such as bills of quantities, contracts, and drawings. Design features that link answers to evidence and make decisions auditable and traceable. Extend multi-modal ingestion of unstructured documents — PDFs, scans, drawings, and 3D models — at scale. Build read/write integrations with customer systems (document management, ERP) to complete workflows end-to-end. Contribute to scalable data pipelines and support native BIM/DWG file processing. What We're Looking For 3+ years of full-stack software engineering experience in fast-paced, B2B startup environments. Proven track record delivering production-grade applied AI features to customers. Proficiency in TypeScript, Python, and SQL for building full-stack applications. Experience building backend APIs and database schemas (e.g. Fastify, Prisma, or equivalent). Experience integrating and optimizing LLM APIs (e.g. OpenAI, Azure, Gemini, Cohere, or similar). Experience with cloud infrastructure such as AWS (RDS, S3, Elastic Beanstalk) or equivalent. Experience building data pipelines and ETL workflows for processing unstructured data at scale. Experience with vector databases and semantic search implementations. Experience designing and implementing evaluation frameworks and error analysis for AI systems. Experience building internal platform or developer-facing tooling that other engineers ship on top of. Startup exposure or early-stage founding experience; comfort with autonomy, ambiguity, and end-to-end ownership. Fluent spoken and written English; German is a genuine plus but not required. Familiarity with workflow orchestration tools (e.g. Prefect, Airflow), document processing/OCR, or observability tooling (e.g. Datadog, Langfuse) is a bonus. Compensation & Benefits Salary range: €80,000 – €120,000 per year. Visa sponsorship is not available for this role. Location On-site, five days per week in Berlin, Germany . Candidates must be based in Berlin or willing to relocate.