At a Glance
- Tasks: Conduct experiments to study AI behaviour and develop automated audit agents.
- Company: White Circle, a leader in AI safety research.
- Benefits: Competitive salary, flexible hours, and opportunities for professional growth.
- Other info: Dynamic work environment with a focus on innovation and collaboration.
- Why this job: Join a cutting-edge team tackling real-world AI challenges and making a difference.
- Qualifications: Experience in AI research and strong analytical skills.
The predicted salary is between 60000 - 80000 £ per year.
White Circle is seeking a research scientist to study how LLM agents fail in the wild, elicit deception, misalignment, and unsafe behaviour in concrete experiments, and build out the understanding of how agents break or misbehave in realistic and user-related scenarios. You will own research projects end to end—from unclear concerns to falsifiable experiments and defensive baselines—and develop automated audit agents that discover suspect model behaviour at scale.
AI Safety Research Scientist: Behavior & Evaluation employer: White Circle
At White Circle, we pride ourselves on being an exceptional employer, offering a dynamic work culture that fosters innovation and collaboration in the field of AI safety. Our team enjoys comprehensive benefits, including paid time off, medical insurance for our France-based employees, and the opportunity to work in vibrant locations like Paris or London, with relocation support available. We are committed to employee growth, providing access to cutting-edge tools and resources, as well as unique team-building experiences that enhance both professional development and camaraderie.
