AI Safety Research Scientist | EA Opportunities Board

The Effective Altruism

Opportunities Board

Work on the world's most pressing problems. Browse jobs, fellowships, internships, courses, and more at high-impact organisations.

Get notified

Submit opportunity Send feedback

Get notified about new roles

AI Safety Research Scientist

Beneficial AI FoundationRemote / Cambridge, USA

Remote / Cambridge, USA

4 months ago

AI safety & policy

Full-time

Routes to impact

Direct high impact on an important cause

Skill-building & building career capital

Description

For experienced researchers in formal verification who want to help ensure advanced AI systems remain under human control.

Research focus – Develop AI-assisted formal verification methods, working with Max Tegmark and collaborators to build AI-written, verified code for safe systems
Impact – Contribute to approaches aimed at guaranteeing safety for transformative AI, including work outlined in Towards Guaranteed Safe AI
Environment – Work remotely worldwide or in Cambridge, MA near MIT, with high autonomy and collaboration
Compensation – $70,000–$180,000 USD per year depending on experience and qualifications

Ideal for strong programmers with deep experience in formal verification (PhD or equivalent experience), who are motivated by mathematical rigor and long-term AI safety challenges.

This text was generated by AI. If you notice any inconsistencies, please let us know using this form

View opportunity

Related opportunities