Lead Research Scientist - AI Safety & Self-Proving Models

Massachusetts Institute of Technology; Cambridge (MA); On-site; USD 80,000 - 120,000; Full time

Job summary

The Massachusetts Institute of Technology seeks a Research Scientist 3 in Cambridge, MA, to lead a research program focused on Provable AI Safety. This role involves advancing AI safety research by establishing both theoretical foundations and practical implementations of self-proving AI systems.

As a key member of the research team, you will supervise PhD students, set the research direction for the program, and publish findings in top scientific forums. Candidates should have expertise in theoretical computer science and machine learning.

Qualifications

• Experience in theoretical computer science and machine learning.
• Ability to supervise PhD students and lead research programs.
• Strong publication record in AI safety and formal verification.

Responsibilities

• Lead a research program on Provable AI Safety.
• Build theoretical foundations of AI systems.
• Supervise PhD students and publish research outcomes.

Job description

The Massachusetts Institute of Technology seeks a Research Scientist 3 in Cambridge, MA, to lead a research program focused on Provable AI Safety. This role involves advancing AI safety research by establishing both theoretical foundations and practical implementations of self-proving AI systems.

As a key member of the research team, you will supervise PhD students, set the research direction for the program, and publish findings in top scientific forums. Candidates should have expertise in theoretical computer science and machine learning.