Safety Jevroni (Contract, 6 weeks)

The role

A safety researcher will build evals and investigate concerning model behavior. The role involves documenting observations and writing a departure post.

What you will do

• 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.

Required qualifications

• 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.

Before you apply

• Submit a draft of your eventual resignation post.

About the company

TypeSafe is an AI lab pushing frontier model intelligence in a new direction. They are a small, fast team backed by a $870M Series A led by a16z.