AI Offense-Defense Dynamics Lead Researcher
New
C
CARMAAI risk management
Listing locations: Anywhere; This role is 100% remoteFull-TimeLead
Salary125,000 - 200,000 USD per year
Apply NowOpens the employer's application page
Job Details
- Required Skills
- LLM
Requirements
- Hold an M.Sc. or higher in Computer Science, Cybersecurity, Criminology, Security Studies, AI Policy, Risk Management, or a related field.
- Demonstrate experience with complex systems modeling, risk assessment methodologies, or security analysis.
- Understand dual-use technologies and factors influencing whether capabilities favor offensive or defensive applications.
- Understand modern AI systems, including large language models, multimodal models, and autonomous agents, and be able to analyze their architectures and capability profiles.
- Bring experience in one or more of security mindset, security studies research, cybersecurity, safety engineering, AI governance, operational risk management, systems dynamics modeling, network theory, complexity science, adversarial analysis, or technical standards development.
- Be able to develop qualitative frameworks and quantitative models capturing sociotechnical interactions, including semi-quantitative and semi-empirical models grounded in logic.
- Have relevant publications or research contributions related to technology risk, governance, or security.
- Demonstrate analytical thinking and ability to identify path dependencies and feedback loops in complex systems.
- Occasional travel is required.
Responsibilities
- Develop quantitative system dynamics models of technological, social, and institutional factors influencing AI risk.
- Design analytical models and simulations to identify policy leverage points that could shift offense-defense balances.
- Expand and operationalize the offense/defense dynamics taxonomy and framework, including metrics and models for assessing AI system features.
- Build empirically informed analytical frameworks using documented cases of AI misuse and beneficial deployment.
- Research how AI technical characteristics interact with sociotechnical contexts to determine offense-defense balances.
- Communicate research through blog posts, articles, conference talks, and media engagement.
- Create tools and methodologies to assess new AI models for offense-defense implications.
- Draft evidence-based AI governance guidance and translate findings into actionable recommendations for stakeholders.
View Full Description & ApplyYou'll be redirected to the employer's site
