Safety Jevroni (Contract, 6 weeks)
TypeSafe AI· Engineering
San Francisco OfficeContractPosted 2w ago
About the role
Contract safety researcher position at TypeSafe (6 weeks) focusing on AI safety, alignment, interpretability, and model evaluation with a provocative onboarding and departure narrative.
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.
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.
Skills
Required:AI safetyCommunication / Writing
Last updated Oct 20, 2026. Interested? Apply on the company site.
About TypeSafe AI
TypeSafe AI is an AI lab building machine-native intelligence infrastructure for automation, designed to make decisions within software. Try our first System One Model, Jev, in early access.
System One ModelsJevRLCDReinforcement Learning for Calibrated Decisionscalibrated decisionLLMsTypeSafe AI
More open roles at TypeSafe AI
- Data Demons6d agoSan Francisco Office · Engineering
- Full-Stack/Front-end Engineer6d agoSan Francisco Office · Engineering
- Data Platform Engineer6d agoSan Francisco Office · Engineering
- Console Engineer (Full-Stack)6d agoSan Francisco Office · Engineering
- Software Engineer Generalist6d agoSan Francisco Office · Create your own role