RemoteLeaf Logo
Log in Sign up

AI Offense-Defense Dynamics Lead Researcher

5 months, 1 week ago
Anywhere, United States
Full-time
Lead
AI Research Scientist
Artificial Intelligence and Machine Learning
Cybersecurity LLM
Apply Now
Bluesky

Bluesky

Bluesky is a social media platform that offers a unique and interactive experience for users to connect, create, and have fun. JavaScript is required for its heavily interactive web application.

Internet Software & Services
Founded 2021
View All Jobs 7

Description

  • Develop quantitative system dynamics models of the technological, social, and institutional factors shaping AI risk.
  • Design analytical models and simulations to identify policy leverage points that shift offense-defense balances toward safer outcomes.
  • Expand and operationalize the offense/defense dynamics taxonomy and framework by developing metrics and predictive models.
  • Build empirically informed frameworks using documented cases of AI misuse and beneficial deployments to validate theory.
  • Research how technical characteristics of AI systems interact with sociotechnical contexts to determine offense-defense outcomes.
  • Create tools and methodologies to assess newly released AI models for offense-defense implications.
  • Write blog posts, articles, conference talks, and media-facing materials to build public understanding of offense-defense dynamics.
  • Draft evidence-based AI governance guidance that reflects interdependencies between capabilities and deployment contexts.
  • Translate research findings into actionable recommendations for policymakers, AI developers, security professionals, and standards organizations.

Requirements

  • M.Sc. or higher in Computer Science, Cybersecurity, Criminology, Security Studies, AI Policy, Risk Management, or a related field.
  • Demonstrated experience with complex systems modeling, risk assessment methodologies, or security analysis.
  • Strong understanding of dual-use technologies and the factors that influence offensive versus defensive applications.
  • Deep understanding of modern AI systems, including large language models, multimodal models, and autonomous agents.
  • Experience in 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.
  • Ability to develop qualitative frameworks and quantitative models that capture sociotechnical interactions, including semi-quantitative and semi-empirical modeling.
  • Record of relevant publications or research contributions related to technology risk, governance, or security.
  • Exceptional analytical thinking with the ability to identify non-obvious path dependencies and feedback loops in complex systems.
  • PhD in a relevant field is preferred.
  • Experience with system dynamics modeling, hypergraph techniques, or other complex network analysis methods is preferred.
  • Skills in developing interactive tools or dashboards for risk visualization and communication are preferred.
  • Background in interdisciplinary research bridging technical and social science domains is preferred.
  • Experience quantifying qualitative risk factors or developing proxy metrics for complex phenomena is preferred.
  • Background in compiling and analyzing incident databases or case studies for pattern recognition is preferred.
  • Familiarity with empirical approaches to technology assessment and impact prediction is preferred.
  • Knowledge of international relations theory as it applies to technology proliferation dynamics is preferred.

Benefits

  • $125,000 - $200,000 a year.
  • Good benefits for U.S. employees.
  • 100% remote work.
  • Occasional travel required.
  • Open globally, with U.S.-authorized employees hired as employees and non-U.S. candidates engaged as independent contractors.
  • Opportunity to work on high-impact AI risk management and alignment research.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Jalasoft

Academic Content Developer (AI Optimization & Foundations)

Jalasoft 1K-5K Internet Software & Services

Jala University is seeking a production-focused AI/ML educator to develop practical, industry-aligned software education and build course artifacts that support economic opportunity in underserved regions.

Mexico Colombia Argentina United States Contract Senior AI Research Scientist Instructional Designer
AWS Azure Docker Jupyter Machine Learning Matplotlib NumPy Python PyTorch Scikit-learn
1 day, 10 hours ago
Innodata

Research Data Scientist

Innodata 1K-5K IT Services

Innodata is seeking a Research Data Scientist – GenAI/LLM to conduct research, develop evaluation methodologies, and translate findings into practical AI/ML solutions across Generative AI, LLMs, NLP, multimodal AI, and AI data.

United States Full-time Mid Level AI Research Scientist
$160k-$185k
AWS Azure Feature Engineering Generative AI Git Machine Learning NumPy Pandas Python PyTorch Scikit-learn SQL TensorFlow
6 days, 8 hours ago
Sysdig

Director, Security Research

Sysdig 251-1K IT Services

Sysdig is hiring a senior leader to direct its Threat Research Team, focusing on AI security threats, AI-assisted research methods, and production detection capabilities for Sysdig customers and the Falco community.

United States Full-time Executive AI Research Scientist Security Engineer
$245k-$307k
Kubernetes Linux
1 week ago
Raydar

AI Research Scientist

Raydar Professional Services

Join a nine-person AI infrastructure startup building reliable autonomous-agent systems to develop original research in agent simulation, evaluation, optimization, and continuous learning and turn it into production capabilities.

United States Canada Full-time Mid Level AI Research Scientist
$130k-$200k
Machine Learning Python Reinforcement Learning
1 week ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers