Research Scientist, AI Safety
3 days ago
We're a London-based start-up dedicated to developing safe and beneficial AI systems that will have a profound impact on humanity's future. Our mission is to create the most capable AI evaluation models, and we're seeking talented individuals to join our growing team.
RoleAs an alignment research engineer at Atla, you'll play a crucial role in developing language models as evaluators and using your insights to construct safety guardrails for LLMs. Your responsibilities will include:
- Steering LLMs to become strong evaluators aligned with human preferences through prompting, supervised fine-tuning, and adversarial training.
- Developing comprehensive evaluation and red teaming frameworks, including custom internal tooling, datasets, and metrics for rigorous assessment of alignment and safety risks.
- Collaborating with our founders, advisors, and top-tier researchers to define and steer Atla's evolving AI safety research direction and contribute significant findings to top-tier conferences.
- Working closely with our team to navigate the complexities of AI alignment and build a high-performing applied research organization.
We're looking for exceptional ML engineers with a proven track record in empirical research, including designing and executing experiments, and effectively writing up and communicating findings. Your skills should include:
- Proficiency in training and evaluating language models across GPUs, preferably in PyTorch.
- Strong software engineering experience with software design/architecture skills, preferably in Python.
- Aptitude for distilling and applying ideas from complex research papers in our products.
- Experience at elite AI research labs (OpenAI, DeepMind, Meta, Anthropic, etc.).
We offer a competitive salary, significant equity as one of the first joiners, and the opportunity to make a dent in the universe by engineering safe, beneficial AI systems. If you're passionate about AI safety and want to be part of a driven founding team, we encourage you to apply.
-
Research Scientist in AI Safety
3 days ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
3 days ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
3 days ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
3 days ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
Research Scientist in AI Safety
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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...
-
AI Safety Researcher
3 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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
3 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJoin 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
3 weeks ago
London, Greater London, United Kingdom RI Research Instruments GmbH Full timeAbout the RoleWe are seeking a highly skilled Research Scientist to join our team at RI Research Instruments GmbH. As a Research Scientist, you will play a key role in advancing our research efforts in AI safety and developing beneficial AI systems.Key ResponsibilitiesConduct research in AI safety and develop new methods for automatically red teaming...
-
Research Scientist
3 weeks ago
London, Greater London, United Kingdom RI Research Instruments GmbH Full timeAbout the RoleWe are seeking a highly skilled Research Scientist to join our team at RI Research Instruments GmbH. As a Research Scientist, you will play a key role in advancing our research efforts in AI safety and developing beneficial AI systems.Key ResponsibilitiesConduct research in AI safety and develop new methods for automatically red teaming...
-
Machine Learning Research Scientist
3 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJob 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...
-
Machine Learning Research Scientist
3 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeJob 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
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeAI 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
2 weeks ago
London, Greater London, United Kingdom AI Safety Institute Full timeAI 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
1 week ago
London, Greater London, United Kingdom AI Safety Institute Full timeAI Safety Institute: Mechanistic Interpretability Team LeadAISI is launching a pioneering Mechanistic Interpretability team to tackle 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...
-
Research Scientist
1 week ago
London, Greater London, United Kingdom AI Safety Institute Full timeAI Safety Institute: Mechanistic Interpretability Team LeadAISI is launching a pioneering Mechanistic Interpretability team to tackle 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...
