AI Safety Researcher (6-Week) — Evaluate & Document

TypeSafe AI; San Francisco (CA); On-site; USD 150,000 - 190,000; Full time

Job summary

TypeSafe AI in San Francisco seeks a safety researcher to explore model behavior, raise concerns thoughtfully, and document findings for internal review.

The role covers building evals, interpreting alignment and evaluation results, and communicating clearly when asked to discuss specifics. You’ll join a team of highly talented researchers, with an emphasis on responsible disclosure and internal change from within.

Qualifications

• Strong research background in AI safety, alignment, interpretability, or model evaluation.
• Experience raising concerns calmly, then in writing.
• Ability to say “I can't discuss specifics” and still maintain credibility.
• Genuine belief you can drive change from within the organization.

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.

Skills

AI safety

Calmly raise concerns

Clear written communication

Internal change mindset

Job description

TypeSafe AI in San Francisco seeks a safety researcher to explore model behavior, raise concerns thoughtfully, and document findings for internal review.

The role covers building evals, interpreting alignment and evaluation results, and communicating clearly when asked to discuss specifics. You’ll join a team of highly talented researchers, with an emphasis on responsible disclosure and internal change from within.