Software Engineer - AI
About the Role
This is a full-stack Software Engineer role focused on applied AI, sitting within a 15-person Product and Engineering team at an early-stage B2B construction technology startup. You will own AI features end-to-end, from database schema and LLM optimization through to UI, while also building the platform foundations that let new use cases ship quickly. Your work will directly shape the product experience for construction professionals.
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 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 earn trust in AI output.
Model and evolve the construction ontology and project graph, including entity resolution across documents such as BoQs, contracts, and drawings.
Design features that link answers to evidence and make decisions auditable and traceable.
Extend multi-modal ingestion of unstructured documents, including PDFs, scans, drawings, and 3D models, at scale.
Build read/write integrations with customer systems such as document management and ERP platforms to complete workflows end-to-end.
Contribute to scalable data pipelines and support native BIM/DWG file processing.
What We're Looking For
3 or more years of experience as a full-stack software engineer delivering production-grade applied AI features to customers.
Proficiency with TypeScript, Python, and SQL for building full-stack applications.
Experience building backend APIs and database schemas using frameworks and ORMs such as Fastify and Prisma, or equivalents.
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 providers.
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 build on top of.
B2B product experience, ideally in an early-stage startup or as a founder.
Strong ownership mindset: comfortable designing and shipping solutions end-to-end in small, accountable teams.
Fluent spoken and written English; German is helpful but not required.
Familiarity with workflow orchestration tools (e.g. Prefect, Airflow) is a plus.
Experience with document processing, OCR, or multi-modal data ingestion is a plus.
Experience with observability and monitoring tools (e.g. Datadog, Langfuse) is a plus.
Compensation & Benefits
Salary range: 80,000 to 120,000 EUR annually. 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.