AI Safety & Policy Analyst

As an AI Safety & Policy Analyst, you will be on the front lines of developing safe and responsible AI. You will be responsible for challenging models' safeguards, identifying new vulnerabilities, and creating detailed evaluation rubrics used to train and test next-generation LLMs. The role involves designing adversarial tests and articulating failure rationales to improve model safety.

BS/BA degree or equivalent experience in a relevant field; English Proficiency (Exceptional written and verbal communication); Exceptional Analytical Thinking; Creative & Adversarial Mindset; Strong Policy & Taxonomy Acumen; Willingness to review potentially distressing content for safety evaluations. Responsibilities: Challenging model safeguards; Identifying new vulnerabilities; Creating detailed evaluation rubrics; Designing adversarial tests; Articulating failure rationales. Benefits: Remote work; Flexible schedule; Work on next-generation LLMs.