Senior AI Safety Researcher

We're pushing the boundaries of AI safety research at the AI Safety Institute. As a research scientist, you'll be part of a dynamic team exploring the risks of autonomous AI systems. Your expertise will help us advance the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains. You'll work closely with...

Role OverviewThe AI Safety Institute is seeking a highly skilled Senior AI Safety Researcher to join its Safeguard Analysis Team. The successful candidate will play a key role in researching and developing interventions that secure systems from abuse by bad actors.About the RoleThis is a challenging and rewarding opportunity for an experienced researcher to...

The AI Safety Institute is seeking a highly motivated and talented Research Scientist to join our team in the area of AI safety research. The successful candidate will work on studying, evaluating, and recommending mitigations for extreme risks from autonomous AI systems.Key ResponsibilitiesConduct research on AI safety and risk mitigationDevelop and...

We're focused on addressing extreme risks from autonomous AI systems that can interact with the real world. To do this, we're advancing the state of the art in risk modeling, incorporating insights from other safety-critical and adversarial domains, and developing novel techniques. We're also empirically evaluating these risks through one of the world's...

AI Safety Institute Job OverviewThe Department for Science, Innovation and Technology is seeking a highly skilled Senior AI Research Specialist to join its esteemed team at the forefront of artificial intelligence safety research. This role offers an exceptional opportunity for individuals with expertise in machine learning, large language models, and...

About the RoleWe are seeking a highly motivated and talented Research Scientist to join our Societal Impacts team at the AI Safety Institute. The successful candidate will work with our team to design and run studies that answer important questions about the effect AI will have on society.Key ResponsibilitiesDesign and run studies to evaluate the impact of...

At the AI Safety Institute, we are dedicated to optimizing AI systems for state-of-the-art performance across various risk domains. Our Post-Training Team works tirelessly to fine-tune and scaffold AI models, ensuring they reach their full potential.About the RoleWe are seeking a strong Research Scientist to join our team. As a member of this team, you will...

As advanced AI systems continue to evolve, the potential risks associated with their cyber capabilities pose a significant threat to organizational and individual security. These risks are particularly concerning when combined with other AI risk areas, such as harmful outcomes from biological and chemical capabilities, and autonomous systems.The AI Safety...

Job SummaryWe are seeking a highly skilled Research Scientist to join our Science of Evaluations team at the AI Safety Institute. As a Research Scientist, you will play a key role in conducting applied and foundational research focused on the measurement of frontier AI system capabilities.Key ResponsibilitiesDevelop and apply rigorous scientific techniques...

We are seeking an exceptional Cybersecurity Research Engineer to join our team at the AI Safety Institute. Our goal is to develop first-of-its-kind government-run infrastructure to benchmark the progress of advanced AI capabilities in cyber security. The selected candidate will work closely with a cross-functional team of cybersecurity researchers, machine...

Key ResponsibilitiesThe successful candidate will play a crucial role in shaping the AI Safety Institute's approach to AI safety, working closely with the Research Unit to develop and implement safety frameworks and guidelines.Key TasksDevelop and maintain safety frameworks and guidelines for AI development and deploymentCollaborate with the Research Unit to...

We are advancing the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while developing novel techniques. Our research aims to empirically evaluate these risks by building one of the world's largest agentic evaluation suites and pushing forward the science of model evaluations.Job RoleYou will work as...

We are seeking a highly skilled Senior Research Manager to lead our team of scientists and engineers in the development of novel techniques for risk modeling and evaluation of autonomous AI systems.Key Responsibilities:Managing a multi-disciplinary team of scientists, engineers, and domain experts to advance the state of the science in risk modeling and...

The Post-Training Team at the AI Safety Institute is dedicated to optimizing AI systems for state-of-the-art performance in various risk domains. This involves a combination of scaffolding, prompting, supervised and RL fine-tuning of AI models.Key Responsibilities:Improve model performance using cutting-edge machine learning techniquesDevelop methodologies...

About the RoleWe are seeking a highly skilled Workstream Lead to spearhead our Systemic Safety and Responsible Innovation team. As a key member of our leadership team, you will be responsible for developing and delivering a strategy to advance systemic AI safety research, shaping a market-shaping agenda, and building a multidisciplinary team focused on...

AI Safety Institute Research OpportunityThe AI Safety Institute is seeking talented researchers to join its Safeguard Analysis Team. This team focuses on developing and analyzing interventions to secure AI systems from abuse by bad actors.Key Responsibilities:Conduct research on AI security threats and interventionsDevelop and analyze attacks and protections...

We're advancing the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while developing novel techniques. Our research focuses on extreme risks from autonomous AI systems, capable of interacting with the real world. As a risk modelling researcher, your work will span the full space of risks from...

Are you passionate about improving AI systems for safer and more reliable operation? Do you have expertise in machine learning and a strong desire to apply it to real-world problems?We are seeking a talented Research Scientist to join our Post-Training Team at the AI Safety Institute. As a member of this team, you will be responsible for developing and...

Atla is dedicated to developing safe, beneficial AI systems with a profound impact on humanity's future. As a leading London-based startup, we're building the most advanced AI evaluation models. We're seeking an exceptional individual to join our team and collaborate with industry leaders to shape the future of AI.As Atla's alignment researcher, you'll be...

The AI Safety Institute is seeking a highly skilled Research Engineer to join our team in the field of AI safety. The successful candidate will be responsible for studying, evaluating, and recommending mitigations for extreme risks from autonomous AI systems. This includes risk models such as auto-replication, iterative self-improvement, and large-scale...