The role involves building tools for AGI safety research, focusing on model evaluation and analysis.
Added todayLondon, UKAI Safety & Alignment£100K-£200K / year
504 active roles found
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.
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 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.
The role involves running evaluations on frontier AI systems to assess risks, including pre-deployment evaluations and analyzing model behavior.
Research and develop methods to detect and mitigate deceptive behaviors in AI systems, collaborating with AI labs and designing experiments to study model behaviors.
The role involves developing methods to mitigate false information in large language models, creating evaluation protocols, and conducting research in LLM security and interpretability.
The AI Behaviour Engineer role involves building AI evaluation methods to assess model behaviors, focusing on policy and oversight needs, and executing evaluations to address harmful model behaviors.
The Senior Research Engineer will lead ML research projects focused on advancing AI safety through robustness, honesty, and transparency.
Lead high-impact research on AI safety, focusing on experiments related to AI honesty, robustness, and transparency.
PhD fellowship focused on researching mechanistic interpretability methods to enhance the security of large language models and address misinformation.
Internship focused on advancing Responsible AI through projects on AI policy, regulation, and ethical implications.
The role involves organizing international dialogues and events focused on general-purpose AI issues, emphasizing security and coordination.
The role involves designing and implementing security measures for AI workloads and infrastructure, addressing safety and responsible development concerns.
The AI Engineer role involves designing and maintaining an adversarial AI evaluation platform and evaluating AI models' performance and risks.
The AI Policy Officer will monitor compliance of generative AI models with the EU AI Act and assess industry responses to enforcement decisions.
The role involves developing AI systems for risk assessment, conducting research on AI model behavior, and designing evaluation pipelines for safety and reliability.
The Anthology Fund focuses on investments in trust and safety tooling that enhances AI safety and supports responsible AI deployment.
The role involves building tools to monitor AI coding agents for safety and security failures, developing data processing pipelines, and creating visualizations of AI behaviors.