Research Scientist/Engineer (Agentic Systems)

The role

You will build autonomous, large-scale environments to study how single and multi-agent LLMs fail. You will run end-to-end experiments, catalogue failure modes, and turn findings into internal models and public writeups.

What you will do

• Build adversarial environments for agents
• Build realistic multi-agent environments and instrument them
• Run experiments end to end against external APIs and internal models
• Catalogue concrete agent failure modes
• Build tooling to surface failure modes at scale
• Turn findings into internal models of agent behaviour and public writeups

Required qualifications

• Built at least one non-trivial agent environment or automated research pipeline that ran end to end
• Strong software and AI engineering skills
• Can independently orchestrate many agents and containers in parallel
• Track record of empirical research in agents, red-teaming, or post-training
• Ability to turn fuzzy concerns into concrete, falsifiable experiments
• AI power-user fluent with frontier models and coding agents

Nice to have

• 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 methodology fragility
• 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

Benefits

• Competitive compensation, including equity
• Flexible time off
• Relocation support if moving to Paris, available after probationary period
• Premium private health insurance
• Mental health support, including coverage for therapy
• Lunch and dinner covered when working from the office
• Learning and development support for courses, conferences, and opportunities
• All hardware, subscriptions, tools, and services provided
• Team off-sites twice a year

Before you apply

• Intro call with Talent
• Test assignment
• Technical interview with Head of Fundamental Research
• Final interview with CEO

About the company

White Circle is an AI Safety company building the safety, reliability, and optimization layer for AI systems. They process over 100M+ API calls every month and fine-tune their own LLMs.