Join LawZero in Montreal as a Mathematical Scientist focusing on AI safety research. Collaborate with top experts to develop safe-by-design systems and theoretical blueprints.

This is an exceptional opportunity to influence the future of AI systems while working with esteemed researcher Yoshua Bengio. You will tackle complex theoretical and safety challenges that impact AI deployment, contributing to research that prioritizes safety and capability. Engage in empirical validation and share your insights with engineering teams to enhance ML algorithms.

Key Responsibilities:
• Develop new AI architectures with safety guarantees
• Refine formal safety requirements with leading researchers
• Analyze and publish findings from existing research
• Keep current with AI safety literature
• Prioritize experiments addressing critical AI safety issues

Requirements:
• PhD in a related field such as statistics or computer scie...