4 hours ago
Berlin, GermanyMid Level
Responsibilities
- Build and own end-to-end AI features, including document versioning and agentic chat workflows, from database schema through UI.
- Manage evaluations, scoring, and error analysis for new and shipped AI features.
- Contribute to workflow harnesses, decision-trace standards, and evaluation tooling.
- Build reusable human-review and approval interfaces for AI outputs.
- Model and evolve construction-domain ontologies and project graphs, including entity resolution across bills of quantities, contracts, and drawings.
- Design features that link answers to evidence and make decisions auditable and traceable.
- Extend multimodal ingestion of PDFs, scans, drawings, and 3D models at scale.
- Build read/write integrations with document management platforms, ERPs, and other customer systems.
- Contribute to scalable data pipelines and native BIM and DWG file processing.
Requirements
- At least 3 years of experience as a full-stack software engineer delivering production-grade applied AI features to customers.
- Proficiency with TypeScript, Python, and SQL.
- Experience building backend APIs and database schemas with frameworks such as Fastify, Prisma, or equivalents.
- Experience integrating and optimizing LLM APIs such as OpenAI, Azure, Gemini, or Cohere.
- Experience with cloud infrastructure such as AWS, RDS, S3, and Elastic Beanstalk, or equivalents.
- Experience building data pipelines and ETL workflows for unstructured data at scale.
- Experience with vector databases and semantic search implementations.
- Experience designing and implementing AI evaluation frameworks and error analysis.
- Experience building internal platform or developer-facing tooling used by other engineers.
- B2B product experience in a startup or early-stage company environment.
- Fluent spoken and written English.
- German language ability is a bonus but not required.
- Experience with workflow orchestration tools such as Prefect or Airflow, document processing or OCR, and observability tools such as Datadog or Langfuse is nice to have.
Benefits
- Salary range of 80,000 to 120,000 EUR annually.
- On-site work five days per week in Berlin, Germany.
- Candidates must be based in Berlin or willing to relocate.
- Visa sponsorship is not available for this role.