Safety Jevroni (Contract, 6 weeks)
TypeSafe AI is hiring for Safety Jevroni (Contract, 6 weeks) in San Francisco Office. Intern level. First seen October 21, 2026; open as of November 11, 2026. Jobs taken straight from company career pages — no aggregator in between.
With Destava: How well do you fit? · Tailor my résumé · Write a cover letter
- Company
- TypeSafe AI
- Where
- San Francisco Office
- Level
- Intern
- First seen
- October 21, 2026
- Listed via
- Ashby
What the posting says
WHAT YOU'LL 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 that makes people concerned enough to share it, despite containing almost no information. WHAT YOU BRING - 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…
Read more and apply on TypeSafe AI's site
More jobs like this
A search agent finds the jobs this list misses: the ones that mean the same without the same words. Have Destava watch for safety jevroni (contract, 6 weeks) jobs in San Francisco Office, new matches every morning on your own account.