AI Safety Argumentation Platform Research Engineer

CARMA is building an evidentiary infrastructure to systematize arguments about AI catastrophe risks, combining ontologies, knowledge graphs, and defeasible argumentation frameworks with LLM-assisted population pipelines. As a Research Engineer, you will develop and operate this platform, working at the intersection of argumentation theory and agentic AI tooling. You will help structure complex arguments for policymakers, technical audiences, and the public. This is a 100% remote role with occasional travel.

• Extend ontologies and knowledge graph schemas representing claims, evidence, argument structures, defeaters, and confidence.
• Implement defeasible argumentation frameworks such as ASPIC+, Dung-style, and argumentation schemes.
• Operate and quality-control LLM-driven population pipelines with cross-check scaffolds, provenance tracking, and human-in-the-loop curation.
• Architect agent coordination patterns for multi-step research and population tasks with robust error handling.
• Build export pipelines translating structured argumentation into diverse communications formats.
• Maintain current awareness across AI safety, capabilities, and governance to keep graph content up to date.

• Working familiarity with formal or semi-formal argumentation theory.
• Experience with ontology engineering or knowledge graph development (OWL/RDF, property graphs, or equivalent).