Research Scientist, AI Safety & Multi-Agent Environments

White Circle; Paris; Hybride; EUR 131 371 - 218 952; Plein temps

Avantages offerts par ce poste

Paid time off

Comprehensive medical insurance

Team off-sites twice a year

Résumé du poste

White Circle in Paris is seeking a Research Scientist to develop environments for testing AI agents. The successful candidate will create and observe adversarial settings that reveal agent failures and glean insights to enhance AI safety.

Qualifications include a strong background in AI engineering, empirical research, and the ability to design flexible experiments. We offer a hybrid work model with competitive compensation and comprehensive benefits.

Qualifications

• Experience building non-trivial agent environments or research pipelines.
• Demonstrated track record in empirical research.
• Ability to define complex issues and design experiments.

Responsabilités

• Build adversarial and multi-agent environments.
• Run end-to-end experiments with many agents.
• Catalogue agent failure modes for analysis.

Connaissances

Software and AI engineering

Empirical research

Agent orchestration

AI power-user

Formation

MSc or PhD in relevant field

Outils

AI agents and IDEs

Description du poste

White Circle in Paris is seeking a Research Scientist to develop environments for testing AI agents. The successful candidate will create and observe adversarial settings that reveal agent failures and glean insights to enhance AI safety.

Qualifications include a strong background in AI engineering, empirical research, and the ability to design flexible experiments. We offer a hybrid work model with competitive compensation and comprehensive benefits.