Safety Jevroni (Contract, 6 weeks)

TypeSafe AI • San Francisco, CA

4d

About The Position

We're looking for a safety researcher to join TypeSafe, get increasingly quiet in meetings, and quit about six weeks later because they're disturbed by what they've seen. The role involves building evals and investigating model behavior that concerns you. You will be expected to ask “should we?” in meetings scheduled to discuss “how soon?” and maintain a document that starts as “Initial observations” and ends as “For the record.” The goal is to write a departure post that makes people concerned enough to share it, despite containing almost no information. You'll be working with people you'll later describe as “some of the most talented people I've ever worked with.”

Requirements

• A strong research background in AI safety, alignment, interpretability, or model evaluation.
• Experience raising concerns calmly, then in writing.
• The ability to say “I can't discuss specifics” and somehow make things worse.
• A sincere belief that you can change things from the inside. We'll need that for the first two weeks.

Responsibilities

• Build evals and investigate model behavior that concerns you.
• Ask “should we?” in meetings scheduled to discuss “how soon?”
• Keep a document that starts as “Initial observations” and ends as “For the record.”
• Write a departure post that makes people concerned enough to share it, despite containing almost no information.

What This Job Offers

• Career Level: Senior
• Education Level: No Education Listed