Data Engineer

Complir is building an AI platform for product compliance, turning global regulatory text into structured, queryable data. As Data Engineer, you’ll own the crawling, parsing, and change-detection pipelines that keep the platform’s regulatory data current and provably correct. You’ll work on-site in Copenhagen alongside founders, AI engineers, and compliance experts.

• Build and operate crawling and monitoring across hundreds of regulatory sources.
• Parse raw legal text (HTML, PDFs, scans) into a normalized requirement schema using LLM-assisted extraction.
• Build change detection that catches new acts, amendments, and repeals the day they land and triggers downstream updates.
• Own data quality end to end: provenance, versioning, and coverage metrics.
• Shape the architecture, tooling, and data culture as the team grows.

• Several years building data pipelines, crawling infrastructure, or large-scale extraction systems.
• Experience with or strong interest in LLM-assisted extraction: structured outputs, evals, and failure modes of models reading dense text.
• Treat data correctness as sacred — provenance, versioning, and traceability.
• Comfortable with messy sources: broken HTML, scanned PDFs, and multilingual legal prose.
• Product-minded and able to thrive in a fast-moving, small-team environment.