Current jobs related to AI Safety Research Scientist - London, Greater London - Department for Science, Innovation & Technology


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyThe AI Safety Institute research unit is seeking highly motivated and talented Research Scientists to work on critical areas of AI safety, including risk models, frontier models, and large-scale targeted manipulation and deception.Key Responsibilities:Conduct research on AI safety and risk models, including...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyThe AI Safety Institute research unit is seeking highly motivated and talented Research Scientists to work on critical areas of AI safety, including risk models, frontier models, and large-scale targeted manipulation and deception.Key Responsibilities:Conduct research on AI safety and risk models, including...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyWe're a team of scientists, engineers, and domain experts at the AI Safety Institute, focused on mitigating the risks associated with autonomous AI systems. Our mission is to advance the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyWe're a team of scientists, engineers, and domain experts at the AI Safety Institute, focused on mitigating the risks associated with autonomous AI systems. Our mission is to advance the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyWe're a team of scientists, engineers, and domain experts at the AI Safety Institute, focused on mitigating the risks associated with autonomous AI systems. Our goal is to advance the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while developing...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyWe're a team of scientists, engineers, and domain experts at the AI Safety Institute, focused on mitigating the risks associated with autonomous AI systems. Our goal is to advance the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while developing...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyWe're a team of scientists, engineers, and domain experts at the AI Safety Institute, focused on mitigating the risks associated with autonomous AI systems. Our mission is to advance the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Team as a Research Scientist in AI SafetyWe're a team of scientists, engineers, and domain experts at the AI Safety Institute, focused on mitigating the risks associated with autonomous AI systems. Our mission is to advance the state of the science in risk modeling, incorporating insights from safety-critical and adversarial domains, while...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    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...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Research TeamThe AI Safety Institute is seeking highly motivated and talented Research Scientists to work on critical projects related to AI safety. Our team is dedicated to advancing the field of AI safety research and developing innovative solutions to mitigate risks associated with autonomous AI systems.Key ResponsibilitiesConduct research on AI...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Join Our Research TeamThe AI Safety Institute is seeking highly motivated and talented Research Scientists to work on critical projects related to AI safety. Our team is dedicated to advancing the field of AI safety research and developing innovative solutions to mitigate risks associated with autonomous AI systems.Key ResponsibilitiesConduct research on AI...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    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...

  • AI Safety Researcher

    1 month ago


    London, Greater London, United Kingdom AI Safety Institute Full time

    Join the AI Safety Institute TeamAISI is launching a new Mechanistic Interpretability team to research the fundamental question of how can we tell if a model is scheming? This is an ambitious bet to bring interpretability as a field into prime time. We believe that this is a vital challenge that mechanistic interpretability can help solve, ensuring that...

  • AI Safety Researcher

    4 weeks ago


    London, Greater London, United Kingdom AI Safety Institute Full time

    Join the AI Safety Institute TeamAISI is launching a new Mechanistic Interpretability team to research the fundamental question of how can we tell if a model is scheming? This is an ambitious bet to bring interpretability as a field into prime time. We believe that this is a vital challenge that mechanistic interpretability can help solve, ensuring that...

  • Research Scientist

    2 weeks ago


    London, Greater London, United Kingdom AI Safety Institute Full time

    Unlock the Secrets of AI SafetyAISI is pioneering a groundbreaking Mechanistic Interpretability team to tackle the fundamental question of how can we ensure AI models are safe and transparent? This ambitious project aims to bring interpretability to the forefront, ensuring that AI systems can be reliably evaluated for safety and alignment. We're seeking a...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Job Title: Machine Learning Research ScientistJoin the AI Safety Institute as a Machine Learning Research Scientist and contribute to the development of safety cases for AI systems. As a key member of our research team, you will conduct foundational research to advance the understanding of AI safety and governance.About the RoleWe are seeking a highly...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Job Title: Machine Learning Research ScientistJoin the AI Safety Institute as a Machine Learning Research Scientist and contribute to the development of safety cases for AI systems. As a key member of our research team, you will conduct foundational research to advance the understanding of AI safety and governance.About the RoleWe are seeking a highly...

  • Research Scientist

    4 weeks ago


    London, Greater London, United Kingdom AI Safety Institute Full time

    AI Safety Institute: Launching a New Mechanistic Interpretability TeamAISI is embarking on a groundbreaking project to develop mechanistic interpretability, a crucial challenge in ensuring the safety of AI systems. We seek a team lead, research scientists, and research engineers to join our mission.Key Responsibilities:Conduct hands-on mechanistic...

  • Research Scientist

    4 weeks ago


    London, Greater London, United Kingdom AI Safety Institute Full time

    AI Safety Institute: Launching a New Mechanistic Interpretability TeamAISI is embarking on a groundbreaking project to develop mechanistic interpretability, a crucial challenge in ensuring the safety of AI systems. We seek a team lead, research scientists, and research engineers to join our mission.Key Responsibilities:Conduct hands-on mechanistic...


  • London, Greater London, United Kingdom AI Safety Institute Full time

    Job Title: Machine Learning Research ScientistWe are seeking a highly skilled Machine Learning Research Scientist to join our team at the AI Safety Institute. As a key member of our research unit, you will play a critical role in advancing our understanding of AI safety and developing innovative solutions to mitigate risks associated with AI systems.About...

AI Safety Research Scientist

2 months ago


London, Greater London, United Kingdom Department for Science, Innovation & Technology Full time

Position Overview

About the Department for Science, Innovation & Technology

The Department for Science, Innovation & Technology is committed to promoting the safe and responsible development of artificial intelligence. Our mission is to ensure that AI technologies are developed with a focus on safety and societal benefits.

We are on an ambitious path and are focused on:

Conducting evaluations of advanced AI technologies. Assessing safety and security, characterizing capabilities, and analyzing societal implications.Developing tools for AI governance. Creating practical frameworks and innovative methods to evaluate safety and societal impacts, while anticipating the influence of future safety research on AI governance.Enhancing information sharing. Establishing effective communication channels between the Department and national/international stakeholders, including policymakers.

Our team consists of experienced professionals from leading tech companies, startups, and government sectors, as well as academic experts in machine learning. We are looking for top talent to contribute to the advancement of global AI safety.

As AI models become increasingly powerful, our commitment to advocating for safe and responsible AI practices is more crucial than ever.

Core Values:

Diversity of Thought: We believe that a variety of perspectives is essential for our success, particularly encouraging contributions from underrepresented groups.Collaborative Environment: We thrive on teamwork and open collaboration, valuing every contribution.Innovation and Impact: We are dedicated to making meaningful changes in AI safety, fostering bold and innovative ideas.Inclusive Culture: We strive to create a supportive workplace where individuals feel valued and empowered to express themselves, leveraging diversity for innovation and informed decision-making.

Role Responsibilities

As a researcher on the Cyber Evaluations Team, you will work alongside cybersecurity and policy experts to evaluate AI system capabilities across various scenarios. Your responsibilities will include conducting experiments on advanced models, analyzing outcomes, and improving tools for assessing and understanding risks associated with advancements in model capabilities.

Candidate Profile

We are seeking a Research Scientist/Engineer with:

Experience in machine learning, artificial intelligence, AI security, or computer security, either in industry or academia.Proficiency in software development, leading relevant projects, and demonstrating effective collaboration skills.A solid understanding of cutting-edge machine learning systems, statistics, and a strong interest in the security implications of AI systems.A proactive, problem-solving approach, high adaptability, and a strong sense of mission and accountability for achieving success.A comprehensive understanding of large language models, such as GPT-4.

Preferred Qualifications

Expertise in Cyber Security.Extensive knowledge of Python, a research background, experience working with multidisciplinary teams, and a track record of raising standards in interviews.

We are hiring for various levels of seniority, including Senior Research Engineer/Scientist roles. The final title, seniority, and compensation will be determined during the recruitment process.

Essential Requirements

Availability for a minimum of 4 days per week.Commitment for a minimum of 12 months.Ability to work in a flexible environment with options for remote work.

Benefits Offered

The Department for Science, Innovation & Technology provides:

Flexible working arrangements.Employer contributions to the pension scheme.Paid annual leave and opportunities for professional development.Employee discounts and a hybrid working policy.