Similar Jobs
See allFellows Program — AI Safety
Anthropic
US
Python
AI Safety
Red Teaming | Generative AI Analyst
Welo Data
US
AI Safety
Data Annotation
Creative Writing
Red Teaming | Generative AI Analyst
Welo Data
US
AI
QA
Testing
Prompt Systems Engineer
Noodle
US
LLM
RAG
Python
Senior Researcher, Civil Safety Sciences
CARMA
Global
AI
Risk Management
Responsibilities:
- Extend ontologies and knowledge graph schemas representing claims, evidence, argument structures, defeaters, and confidence
- Implement defeasible argumentation frameworks (e.g., ASPIC+, Dung-style, argumentation schemes) that capture both logical structure and vulnerability to rebuttal
- Operate and quality-control LLM-driven population pipelines, with cross-check scaffolds, provenance tracking, and human-in-the-loop curation
Required Qualifications:
- Working familiarity with formal or semi-formal argumentation theory
- Experience with ontology engineering or knowledge graph development
- Operational experience with LLM agent systems
CARMA
CARMA works to help society navigate the complex and potentially catastrophic risks arising from increasingly powerful AI systems. They are a fiscally-sponsored project of Social & Environmental Entrepreneurs, Inc., a 501(c)(3) nonprofit public benefit corporation with a mission to lower the risks to humanity and the biosphere from transformative AI.