AI Safety Research Scientist

Beneficial AI Foundation is looking for an AI Safety Research Scientist. This position involves working with Max Tegmark and colleagues on turbocharging formal verification with AI tools. The core idea is to not deploy untrusted neural networks, but AI-written verified code implementing machine-learned algorithms and knowledge.

• Work on formal verification projects with AI tools
• Develop AI-written verified code implementing machine-learned algorithms
• Collaborate with Max Tegmark and colleagues on AI safety research
• Contribute to ensuring powerful AI systems stay under human control

• Significant experience in formal verification, ideally with PhD or extensive work in the field
• Strong programmer
• Likes mathematics and machine learning
• Self-motivated and enjoys working fairly independently
• Concerned about AGI safety and current AI safety approaches

Complete the Google Form provided on the listing page with your full name, email, formal verification background, CV link, LinkedIn profile, publication list, and motivation for the position.