AI Safety Argumentation Platform Research Engineer (AI)

TL;DR

AI Safety Argumentation Platform Research Engineer (AI/LLM): Developing an evidentiary infrastructure to systematize AI risk arguments using knowledge graphs and LLM pipelines with an accent on argumentation theory and agentic AI tooling. Focus on building formally tractable machinery to translate structured argumentation into persuasive communications for policymakers and the public.

Location: Remote (Open Globally)

Salary: $160,000 - $210,000 a year

Company

The Center for AI Risk Management & Alignment (CARMA), a project of hirify.global, focuses on grounding AI risk management in rigorous analysis to lower catastrophic risks from transformative AI.

What you will do

• Extend ontologies and knowledge graph schemas representing claims, evidence, and argument structures.
• Implement defeasible argumentation frameworks (e.g., ASPIC+, Dung-style) to capture logical structure and vulnerability to rebuttal.
• Operate LLM-driven population pipelines with provenance tracking and human-in-the-loop curation.
• Architect agent coordination patterns for multi-step research and population tasks with robust error handling.
• Pre-harden argument structures by mapping the strongest counterarguments and steel-manned objections.
• Build export pipelines that translate structured argumentation into diverse communications formats for various audiences.

Requirements

• Working familiarity with formal or semi-formal argumentation theory (defeasible reasoning, dialectical models).
• Experience with ontology engineering or knowledge graph development (OWL/RDF, property graphs).
• Operational experience with LLM agent systems, prompt engineering at scale, and QC regimes for LLM outputs.
• Substantive grounding in AI safety, AI governance, and current frontier-AI dynamics.
• Familiarity with philosophy of science concepts such as defeaters, burden of proof, and inference to the best explanation.
• Comfort with graph databases, query languages, and strong written communication skills.

Nice to have

• Graduate work in argumentation theory, computational argumentation, epistemology, or philosophy of science.
• Familiarity with computational argumentation tools like AIF or Carneades.
• Track record in AI safety or governance, including publications or policy work.
• Background in argument mining, claim extraction, or stance detection.
• Experience with debate formats or structured deliberation methods.

Culture & Benefits

• 100% remote work arrangement with occasional travel.
• Opportunity to build the epistemic backbone for AI safety communication.
• Inclusive organization that promotes equal opportunities based on individual merit.
• Flexible engagement: US-based employees or international independent contractors.