AI Safety Argumentation Platform Research Engineer
New
AnywhereFull-TimeMiddle
Salary160,000 - 210,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonPrompt Engineering
Requirements
- Working familiarity with formal or semi-formal argumentation theory
- Experience with ontology engineering or knowledge graph development (OWL/RDF, property graphs)
- Operational experience with LLM agent systems: coordination, prompt engineering, and QC regimes
- Fluent LLM-assisted development practice
- Substantive grounding in AI safety, AI governance, and frontier-AI dynamics
- Familiarity with philosophy of science concepts: defeaters, burden of proof, inference
- Good coding skills and comfort with graph databases or query languages
- Experience designing cross-check and verification scaffolds
- Sound judgment regarding claim substantiation
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)
- Operate and quality-control LLM-driven population pipelines with human-in-the-loop curation
- Architect agent coordination patterns for multi-step research and population tasks
- Pre-harden argument structures by mapping counterarguments and objections
- Build export pipelines for structured argumentation to diverse communications formats
- Maintain awareness of AI safety and governance developments
- Collaborate with communications staff and researchers
View Full Description & ApplyYou'll be redirected to the employer's site
