This role focuses on identifying, quantifying, and understanding future AGI misalignment risks far in advance of when they can pose harm
Job Summary
This role focuses on identifying, quantifying, and understanding future AGI misalignment risks far in advance of when they can pose harm.
The successful candidate will design worst-case demonstrations and develop adversarial evaluations to measure dangerous capabilities and residual risks.
You will partner with engineering, research, policy, and legal teams to integrate findings into product safeguards and governance processes.
Matching Summary
This role focuses on identifying, quantifying, and understanding future AGI misalignment risks far in advance of when they can pose harm.
Salary
Not specified; Not specified; Not specified
Skills & Requirements
Must-have
4+ years experience in AI red-teaming
Strong research track record in security
Fluency in modern ML and AI techniques
Ability to hack on large-scale codebases
Experience with adversarial machine learning
Nice-to-have
Passion for building safe universally beneficial AGI
Collaboration across research engineering and policy