AI Scientist, Safety

Overview

Role focused on evaluating and enhancing safety mechanisms for large language models.

Ideal candidate should have a degree in a relevant field and experience in AI safety.

Locations

• United Kingdom, England, London
• France, Île-de-France, Paris

Requirements

• Degree in Computer Science or related field
• Experience in AI safety or related field
• Proficiency in Python and one other programming language

Responsibilities

• Evaluate and enhance safety mechanisms for LLMs
• Design and execute adversarial tests
• Develop monitoring systems for unwanted behaviors
• Investigate incidents of LLM misuse
• Collaborate on safety measures with AI team
• Stay updated on AI safety trends
• Build multi-layered defenses for safety mechanisms

Benefits

• Competitive cash salary
• Equity
• Daily lunch vouchers
• Monthly contribution to Gympass
• Full health insurance
• Generous parental leave policy
• Monthly contribution to mobility pass
• Competitive Healthcare program
• Monthly pension contribution