Research Engineer, AI Safety

Core responsibilities:

• Work with Max Tegmark at the Beneficial AI Foundation to develop AI tools for formal verification of AI systems
• Contribute to research on creating verified code that implements machine-learned algorithms rather than deploying untrusted neural networks
• Apply formal verification techniques to ensure powerful AI systems remain under human control
• Develop mathematical frameworks and programming solutions at the intersection of formal verification and machine learning

This role creates positive change by developing tools and frameworks to ensure powerful AI systems remain under human control and addressing safety challenges of advanced AI systems through formal verification techniques.

Required skills and qualifications:

• Experience with formal verification techniques
• Background in machine learning and AI systems
• Ability to develop mathematical frameworks and programming solutions
• Capability to work independently on projects addressing safety challenges of advanced AI systems

No compensation, perks, or culture highlights mentioned in the job description.

The Beneficial AI Foundation works on developing AI tools for formal verification of AI systems and addressing safety challenges of advanced AI systems.