Źródło:
Safety Jevroni (Contract, 6 weeks)
TypeSafe AI
San Francisco, United States
Publication date: 04/11/2026
TypeSafe is an AI lab pushing frontier model intelligence in a new direction, starting with System One Models. It combines the reasoning of LLMs with the reliability of code. The first model, Jev, launched in September 2026. The team is small and fast, backed by an $870M Series A led by a16z. The role lasts six weeks. Applicants apply by submitting a draft of their eventual resignation post, and may omit specifics.
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 informationRequirements
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"; A sincere belief that you can change things from the insideHow to apply
Apply online: https://www.jobs.pl/en/oferta/103767399/aplikuj
JOBS.pl · https://www.jobs.pl/safety-jevroni-contract-6-weeks-oferta-103767399


