Research Scientist: Frontier AI Risk & Evaluations

Safer Ai; Paris; Hybride; EUR 90 000 - 140 000; Plein temps

Avantages offerts par ce poste

Health insurance

Retirement plans

50% home transportation

Productivity expenditures up to €2k

Office space

Résumé du poste

SaferAI is seeking a Research Engineer or Research Scientist to join the Evaluations team in Paris, with opportunities to influence risk management across frontier AI labs. You will develop threat models, run evaluations, and deliver rigorous reports while advancing safety practices with international partners.

A fast-growing environment, competitive compensation, and flexible remote options are offered. This role emphasizes hands-on AI safety work, collaboration across teams, and delivering

Qualifications

• MS or PhD in computer science, machine learning, AI safety, or related technical field.
• Hands-on experience developing, deploying, or evaluating AI systems in frontier AI contexts.
• Ability to deliver projects in fast-paced and evolving environments.

Responsabilités

• Develop threat models and benchmarks to measure risk.
• Run model evaluations on leading AI models using elicitation best practices and Inspect AI.
• Analyze results and write high-quality technical reports; contribute to safety mitigations and tools.

Connaissances

AI safety

Model evaluations

Threat modeling

Technical writing

Formation

MS/PhD in CS/ML/AI safety

Outils

Inspect AI

AWS

EKS

Description du poste

SaferAI is seeking a Research Engineer or Research Scientist to join the Evaluations team in Paris, with opportunities to influence risk management across frontier AI labs. You will develop threat models, run evaluations, and deliver rigorous reports while advancing safety practices with international partners.

A fast-growing environment, competitive compensation, and flexible remote options are offered. This role emphasizes hands-on AI safety work, collaboration across teams, and delivering