Mathematical Scientist for AI Safety Research

The role

This researcher will explore new AI system architectures, theoretical frameworks, and safety mechanisms to find a blueprint for safe AGI. You will work with Yoshua Bengio to analyze formal requirements, prove probabilistic safety guarantees, and contribute to scientific papers.

What you will do

• Explore new AI system architectures, theoretical frameworks, and new safety mechanisms.
• Analyze and refine formal requirements for building and deploying Scientist AI.
• Prove probabilistic safety guarantees under finite data and compute constraints.
• Help research teams with empirical validation as the system matures.
• Analyze, evaluate and contribute to existing theoretical work.
• Write and disseminate scientific papers.
• Read research to stay up-to-date with AI safety and machine learning.
• Scrutinize and contribute to the broader research agenda to guide experiments.
• Share knowledge to help researchers and engineers design and implement ML algorithms and experiments.

Required qualifications

• A PhD in machine learning, computer science, mathematics, statistics, or an adjacent area relevant to the Scientist AI research program.
• A track record of research, especially in the formalization and fruitful technical analysis of subtle natural-language intuition.
• Strong interest in technical AI safety.
• Exceptional ability for abstract systems thinking.
• A deep understanding of the mathematical underpinnings commonly used in the design and analysis of probabilistic machine learning, especially for neural networks and language models.
• The perseverance to work through hard and ill-defined problems.
• Clear communications: the ability to articulate complex ideas verbally and in writing to both technical and non-technical audiences.
• The ability to work in a collaborative environment and contribute to collective research goals.

Nice to have

• The ability to regularly travel alongside Yoshua and team members to conferences

About the company

LawZero is a non-profit organization based in Montreal committed to advancing research and creating technical solutions that enable safe-by-design AI systems. Its scientific direction is based on new research and methods proposed by Professor Yoshua Bengio.