Research Scientist, Agentic Systems & AI Safety

Whitecircle; Paris; Hybride; EUR 90 000 - 150 000; Plein temps

Avantages offerts par ce poste

Paid time off (local regulations)

Relocation package for Paris or London

Equity package

Medical insurance for France-based팀

All hardware, tools, and services

Résumé du poste

White Circle is seeking a research scientist to build autonomous, large-scale environments that test LLM agents to failure and study how they break. You will conduct end-to-end experiments with external APIs and internal models, focusing on agent behaviours and failure modes to inform safety research and public writeups.

The role emphasizes building non-trivial agent ecosystems, with strong emphasis on engineering, experimentation, and rigorous analysis to advance AI safety in production-like

Qualifications

• 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.
• Strong software and AI engineering. Can independently orchestrate many agents and containers in parallel without that orchestration being the bottleneck.
• 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.
• 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.
• An AI power-user — fluent with frontier models and coding agents in your daily work.

Responsabilités

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

Connaissances

Agent environments

Multi-agent

End-to-end experiments

AI engineering

Experiment design

Formation

MSc/PhD in ML/CS

Outils

APIs

Containers

Description du poste

White Circle is seeking a research scientist to build autonomous, large-scale environments that test LLM agents to failure and study how they break. You will conduct end-to-end experiments with external APIs and internal models, focusing on agent behaviours and failure modes to inform safety research and public writeups.

The role emphasizes building non-trivial agent ecosystems, with strong emphasis on engineering, experimentation, and rigorous analysis to advance AI safety in production-like