The role involves conducting research on AI security, focusing on protecting models against cyber threats and evaluating AI's cybersecurity capabilities.
Added todayTel Aviv, IsraelAI Compliance & Risk Management
499 active roles found
The role involves conducting research on AI security, focusing on protecting models against cyber threats and evaluating AI's cybersecurity capabilities.
The Research Engineer role involves building systems to evaluate and secure frontier AI models, focusing on risk mitigation and security testing.
The Technical Policy Researcher will address AI security issues, conduct threat modeling, develop taxonomies for AI capabilities, and create policy proposals.
A concise digest of alignment, governance, and AI risk jobs.
By subscribing, you agree to receive the AI Safety Careers newsletter. You can unsubscribe at any time. See our Privacy Policy.
The role involves designing and implementing ML models to address advanced AI safety challenges, collaborating with researchers, and developing evaluation frameworks.
The role involves developing and evaluating probabilistic inference methods to support safe-by-design AI systems.
Lead RAND's AI cyber evaluation agenda, focusing on assessing AI models' offensive cyber capabilities and developing benchmarks for performance.
PhD research position focused on AI safety, investigating large language models and evaluating AI systems to ensure safe development.
Lead AI safety research and conduct red teaming for frontier models in sensitive domains.
Lead Faculty's AI safety research team, focusing on safe AI systems and conducting research on large language models.
The Applied AI Engineer role focuses on developing ML methods for assessing biological threats and creating evaluation frameworks for model performance.
The role involves developing AI safety strategies, building evaluations for scientific risks, and creating safeguards against unsafe AI behavior.
The role involves designing and building production systems for evaluating and securing frontier AI models.
Lead AI safety strategy and evaluate risks related to scientific superintelligence in biological and physical sciences.
The role involves designing and implementing safety strategies for AI systems in biological and physical sciences, including risk evaluations and threat modeling.
The role involves designing and building a security evaluation platform for AI agents, focusing on threat models, evaluation schemas, and policy enforcement.
The role involves building tools for AGI safety research, focusing on model evaluation and analysis.
The role involves building tools for AGI safety research, focusing on evaluations and monitoring systems for language models.
The role involves designing methods to ensure AI models align with goals, developing monitoring techniques, researching control mechanisms, and conducting red-team simulations.
The role involves designing evaluation measures for assessing risks from frontier AI systems, building testing harnesses, and collaborating with government agencies on advanced AI risk evaluations.
PhD studentship focused on exploring large language model safety through mechanistic interpretability and behavioral research.