At a Glance
- Tasks: Conduct experiments on AI behaviours and develop automated audit agents to enhance safety.
- Company: Join White Circle, a leading AI Safety company with a focus on reliability and optimisation.
- Benefits: Enjoy competitive pay, comprehensive medical insurance, and flexible work options in Paris or London.
- Other info: Collaborate with top experts and enjoy team off-sites in amazing locations.
- Why this job: Make a real impact on AI safety while working on cutting-edge research and technology.
- Qualifications: Empirical research experience in AI behaviour and strong ML engineering skills required.
The predicted salary is between 80000 - 98000 £ per year.
TLDR: We're looking for a research scientist to study how LLM agents fail in the wild, who can 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.
White Circle is an AI Safety company building the safety, reliability, and optimization layer for AI systems.
At the core of our platform are policies – simple natural‑language rules that define what an AI model should and shouldn’t do.
We automatically test, enforce, and continuously improve these policies at scale.
About Us
- We’ve raised $11M from top funds, founders, and senior leaders at Open AI, Anthropic, Hugging Face, Mistral, Deep Mind, Datadog, Sentry, and others
- We process over 100M+ API calls every month
- We fine‑tune and train our own LLMs so they run faster and cheaper than any open or proprietary model
We’re a small, highly focused team.
If you want to work deeply on hard problems, see your work ship to production quickly, and influence how AI safety is actually built – you’re the one we need.
About The Team
White Circle's fundamental research team works on the science of how AI systems fail: where agents break, why misalignment and unsafe behaviours emerge, and how to catch them before they reach the real world.
We build the evals, benchmarks, environments, and tooling that empirically study the most pressing AI safety concerns — some of which become the guardrails shipped in our products, and some of which become public writeups.
You will
- Own research projects end to end — from an unclear concern ("how do we even define sloppy research outputs?") to a falsifiable experiment, clean baselines, and a result you can defend.
- Develop automated audit agents that discover and characterise suspect model behaviour at scale.
- Study how misalignment and bias actually show up when real users interact with agents, and turn what you find into evals our products can ship.
- Pressure‑test frontier agents in realistic, high‑stakes scenarios to find where they break before our customers do.
- Run white‑box and block‑box investigations to understand how AI models fail.
- Publish what you learn as public blog posts and conference papers, and feed the rest back into our internal guardrails.
You’ll fit right in if you
- A track record of empirical research in agent behaviour, model evaluation, alignment, or a closely adjacent area.
- Strong ML engineering. You can independently build a research MVP involving fine‑tuning, agent inference, and evals, without waiting on a platform team.
- Evidenced skills in experimental design under real conditions: isolating agent failure modes, calibrating judges and baselines, and distinguishing genuine signal from artifact.
- You can take a vague behavioural question and define the experiment that answers it, when there's no playbook — then run it fast and iterate.
- An AI power‑user — fluent with frontier models and coding agents in your daily work.
A big plus
- Published research at A* venues (Neur IPS / ICML / ICLR / ACL and similar).
- Interpretability depth — familiarity with modern interp tooling and concepts (NLAs, SAEs, persona vectors, etc.) and the ability to run whitebox investigations on our internal and open‑source models.
- An MSc or Ph D in machine learning, computer science, cognitive science, computational neuroscience, physics, or a related quantitative field.
- AI safety fellowship (MATS, ASTRA, Anthropic Fellows, etc.), or a comparable self‑directed research record.
- Why White Circle
- Paid time off in line with your local regulations, no matter where you work from.
- Work from Paris (hybrid) with a relocation package available, or work from London (note: we are currently unable to provide relocation support or medical insurance for London‑based roles).
- Comprehensive medical insurance for our France‑based team.
- All the hardware, tools, and services you need.
- Covered subscriptions for AI agents and IDEs.
- Team off‑sites twice a year: we’ve recently been to the Alps and to Saint‑Tropez.
- How We Hire
- Introductory call with HR (25 min)
- Take‑home test task
- Technical interview with Head of Fundamental Research (60 min)
- Final conversation with our CEO (45 min)
Please submit your application in English.
Compensation Range: $150K - $250K
#J-18808-Ljbffr
StudySmarter Expert Advice🤫
We think this is how you could land Research Scientist (AI Behaviours) in London
✨Get Involved in Research Communities
Dive headfirst into the scientific research world by joining relevant communities and forums. Engage in discussions, share your insights, and even attend conferences or seminars in your field. This not only boosts your visibility but can also lead to potential job opportunities—don't forget to connect with like-minded folks!
✨Show Off Your Research Projects
Have you worked on any cool research projects? Make it easy for potential employers to see your work by creating a portfolio or a personal website. This way, when you apply for roles like the one at White Circle, you can point them to your projects and publications, showcasing your expertise directly.
✨Utilise Professional Networks
Networking is key in scientific research. Join professional bodies or organisations related to your field. They often have job boards and resources tailored for job seekers. Make connections with professionals who may know about openings or can give you tips on landing a full-time position.
✨Keep Your Eyes on Openings & Apply Directly
Don’t just rely on job boards! Keep an eye on the careers section of the websites of companies like White Circle. Apply directly through their website because sometimes they post jobs there before anywhere else. Plus, it shows your proactive approach!
We think you need these skills to ace Research Scientist (AI Behaviours) in London
Some tips for your application 🫡
Highlight Your Research Experience:When applying for a full-time role in scientific research, make sure to emphasise your research experience prominently in your CV. Share specific projects you’ve worked on, the methodologies you used, and any significant findings. If you’ve published papers or presented at conferences, definitely include that too – it shows you’re on it in the academic world!
Tailor Your Cover Letter to the Research Area:Your cover letter should reflect your passion for the specific area of research at White Circle. Mention relevant experiences that align with the organisation’s goals or projects. This shows that you’ve done your homework and are genuinely interested in the position – plus, it helps us see how you’d fit into the team dynamics.
Showcase Your Data Analysis Skills:In scientific research, data analysis skills are a big deal! Make sure to detail any relevant analytical tools or software you’re familiar with, like R, Python, or statistical packages. Employers are keen to know you can handle the data-heavy elements of the role, so add specific examples where you’ve used these skills effectively.
Discuss Your Future Research Goals:In your motivation section, it’s a great idea to talk about your future research goals and how they align with the work being done at White Circle. This shows that you’re not just looking for any job, but rather a chance to contribute meaningfully to the field. We love to see applicants who are forward-thinking and enthusiastic about their research journey!
How to prepare for a job interview at White Circle
✨Showcase Your Research Skills
In scientific research, it’s crucial to demonstrate your ability to design and conduct experiments. Come armed with examples of past projects where you've developed hypotheses, collected data, and analysed results. Be ready to discuss any specific methodologies or tools you’ve used, like PCR techniques or statistical software.
✨Prepare for Technical Questions
Expect some technical questions specific to your field. Make sure you're up to speed with recent advancements in scientific research related to the role at White Circle. Brush up on concepts relevant to their projects and be prepared to discuss how you would approach a specific research problem or challenge they might face.
✨Know Your Publications
If you've authored or co-authored any papers, be prepared to discuss them! Highlighting your contributions to published research can really set you apart. It shows not only your expertise but also your ability to communicate complex ideas clearly, which is key in scientific research roles.
✨Exhibit Your Team Spirit
In full-time roles, collaboration is often at the heart of scientific research. Prepare examples that show how you've successfully worked in teams, dealt with conflicts, or contributed to group projects. We want to know how you can work effectively with the team at White Circle to drive research projects forward.
