Mathematical Scientist, AI Safety Research at LawZero - ScoutJobs - The AI-curated global job board
Skip to content
L
Posted 18 hours ago

Mathematical Scientist, AI Safety Research

LawZero

Perks & benefits

Health InsurancePaid Leave

Requirements

PhD in machine learning, computer science, mathematics, statistics, or adjacent area, Track record of research and formalizing subtle technical intuition, Strong interest and ideally experience with technical AI safety, Deep understanding of probabilistic ML for neural networks and language models, Perseverance to work through hard and ill-defined problems, Clear communication of complex ideas to technical and non-technical audiences, Ability to work collaboratively and contribute to collective research goals

Skills

Machine LearningAINeural Networks

About the role

Responsibilities

  • Explore new AI architectures, theoretical frameworks, and safety mechanisms toward a blueprint for safe AGI with probabilistic guarantees
  • Analyze and refine formal requirements for safe deployment of the Scientist AI alongside senior researchers
  • Prove probabilistic safety guarantees under finite data and compute constraints
  • Evaluate existing theoretical work and contribute to scientific papers
  • Stay current on AI safety and machine learning research, including misalignment and reward hacking risks
  • Guide and prioritize experiments to answer critical safety questions efficiently
  • Support researchers and engineers in designing and implementing new ML algorithms and experiments

Requirements

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

Preferred Qualifications

  • Willingness to regularly travel to conferences with the team

Benefits

  • Comprehensive health benefits including mental health and wellness account
  • 20 days of vacation per year from start date
  • Employer retirement contribution of 4% with no required employee match
  • Additional compensation of 8% of salary toward retirement or bonuses
  • Collaborative office environment in Montreal’s Mile-Ex district

About the Company

LawZero is a non-profit organization advancing research and technical solutions for safe-by-design AI systems. Founded by Yoshua Bengio, it aims to build non-agentic AI that learns to understand the world through transparent probabilistic reasoning, accelerating scientific discovery and providing oversight for agentic AI systems.

ScoutJobs Agent

Get matches like this delivered daily

Sign up free — we'll pull jobs that fit your CV from across the web and rank them for you.

Get started — it's free

Mathematical Scientist, AI Safety Research

LawZero · Montreal

Sign up to apply