Mathematical Scientist for AI Safety Research
On-site · Montréal, Quebec, Canada
Job Summary
The role is a theoretical researcher focused on foundational AI safety research within LawZero, collaborating with Yoshua Bengio and a world-class team to develop a safe-by-design Scientist AI. Responsibilities include exploring new AI system architectures and safety mechanisms, proving probabilistic safety guarantees under finite data and compute constraints, refining formal requirements for safe deployment, evaluating and contributing to existing theoretical work, reading current AI safety literature, guiding experiments, and sharing knowledge with researchers and engineers. Nice-to-have travel aligned with conferences to accelerate work.
Required Qualifications
- A PhD in machine learning, computer science, mathematics, statistics, or an adjacent area relevant to the Scientist AI research program.
- Track record of research focused on formalization and technical analysis of natural-language intuition.
- Strong interest and experience with technical AI safety and abstract systems thinking.
- Deep understanding of probabilistic machine learning foundations for neural networks and language models.
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.