Mathematical Scientist for AI Safety Research

Highlights

• Build a safe-by-design Scientist AI blueprint with probabilistic guarantees.
• Work directly with Yoshua Bengio on foundational AI safety research.
• Explore new architectures and safety mechanisms for safe AGI.

Ideal candidate

Deep abstract thinker with a theoretical research background who thrives on hard, ill-defined problems. Passionate about AI safety and building provably safe, truth-seeking AI for public good.

Requirements

• PhD in machine learning, computer science, mathematics, statistics or adjacent area
• Track record formalizing and analyzing subtle natural-language intuition
• Strong interest and ideally experience in technical AI safety with abstract systems thinking
• Deep understanding of probabilistic machine learning math for neural networks and language models
• Perseverance through hard, ill-defined problems using confusion as a guide
• Clear communication of complex ideas to technical and non-technical audiences
• Ability to work collaboratively toward collective research goals