TL;DR: We're looking for a research scientist to build autonomous, large-scale environments that push LLM agents (single and multi-agent) to failure, and study how they actually break.

About us

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.

We’ve recently raised our Series A funding round, taking our total funding to $70M. Our investors include top funds, founders, and senior leaders at OpenAI, Anthropic, HuggingFace, Mistral, DeepMind, 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.

What you’ll do

Build adversarial environments for agents: complex, uncertain settings that sit on the boundary of agent capability and alignment, where failure is informative rather than trivial.

Build realistic multi-agent environments and instrument them so emergent breakdowns are observable — failures that arise from the agents themselves, not ones scripted from the outside.

Run experiments end to end, against external APIs and our own models, orchestrating many agents in parallel.

Catalogue concrete agent failure modes and build the tooling to surface them at scale.

Turn findings into internal models of agent behaviour and into public writeups.

You’ll fit right in if you

Have built at least one non-trivial agent environment or automated research pipeline that ran end to end (single- or multi-agent), and can talk through what broke and why.

Have strong software and AI engineering skills. Can independently orchestrate many agents and containers in parallel without that orchestration being the bottleneck.

Have a track record of empirical research in agents, red-teaming, or post-training where you defined the question, ran it, and drew a defensible conclusion.

Are a fast empirical iterator who is comfortable defining the question when there's no playbook: can take a fuzzy concern ("do these agents collude under pressure?") and turn it into a concrete, falsifiable experiment.

Are an AI power-user — fluent with frontier models and coding agents in your daily work.

A big plus

Published research at A* venues on automated red-teaming, agentic environments, or post-training.

Experience building monitoring for model failures and anomalous behaviour.

Experience reproducing public benchmark results and finding where the original methodology is fragile or misleading.

An MSc or PhD 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.

Compensation & benefits

Competitive compensation, including equity

Flexible time off

Office in central London/Paris with flexible hybrid setup

Relocation support if you’re moving to Paris, available after your probationary period

Premium private health insurance

Mental health support, including coverage for therapy when you need it

Lunch and dinner covered when you work from the office

Learning and development support for courses, conferences, and opportunities to grow your skills