7 active roles found for AI Security Institute
The AI Security Institute is seeking expressions of interest for a Red Team role focused on AI safety and security, evaluating vulnerabilities, misalignment, and stress testing AI safeguards.
Lead the Control sub-team at the AI Security Institute, focusing on AI safety through stress-testing control measures and managing a team of researchers.
The Senior Software Engineer will design and build systems for the Chem-Bio team, focusing on AI capabilities related to chemical and biological misuse, supporting research and informing policy decisions.
The Senior Engineering Lead will oversee the engineering function within the Chem-Bio team, focusing on building systems that support research on AI capabilities and their implications for security and policy.
The role involves researching and engineering solutions to study the societal impacts of AI, focusing on risks and mitigation strategies.
The AI Security Institute seeks Research Engineers and Scientists for the Model Transparency team, focusing on technical AI safety, model transparency, and alignment evaluations.
The Research Assistant will support the Human Influence team in studying the impacts of frontier AI systems on human behavior and developing strategies for safe AI development.
Get the best AI safety, governance, policy and responsible AI roles in your inbox.
No spam. Unsubscribe anytime. See our Privacy Policy.