AI Safety Researcher — Investigate Model Behavior & Impact

Typesafe AI, Inc.; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

TypeSafe in San Francisco seeks a safety researcher to build evals, investigate concerning model behavior, and contribute to rigorous safety discussions. You will document observations from project start to formal records and draft internal communications.

You will work with highly talented researchers focused on AI safety, alignment, and interpretability, collaborating across teams to strengthen safety review processes.

Qualifications

• 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 still communicate clearly.
• A sincere belief that you can change things from the inside during early weeks.

Responsibilities

• Build evals and investigate model behavior that concerns you.
• Ask “should we?” in meetings discussing timelines and priorities.
• Keep a document that starts as “Initial observations” and ends as “For the record.”
• Write a departure memo that prompts reflection while maintaining discretion.

Skills

AI safety research

Model evaluation

Interpretability

Calmly raising concerns

Job description

TypeSafe in San Francisco seeks a safety researcher to build evals, investigate concerning model behavior, and contribute to rigorous safety discussions. You will document observations from project start to formal records and draft internal communications.

You will work with highly talented researchers focused on AI safety, alignment, and interpretability, collaborating across teams to strengthen safety review processes.