Summary

The Materials Knowledge Architect designs scientific data models and ingestion pipelines for experimental and computational materials data at CuspAI. The role works across materials science, chemistry, and AI, using Python, SQL, and tools such as Pydantic and pymatgen. It is hybrid, with three days per week in an office in Cambridge, London, Amsterdam, or Berlin.

Responsibilities

• Design interoperable scientific data models and schemas
• Build ingestion pipelines for partner datasets
• Harmonize experimental and computational materials data
• Establish validation, deduplication, lineage, and provenance frameworks
• Map external schemas and resolve data issues
• Translate research requirements into ML-ready datasets