Search
Go
Senior Staff ML Engineer - AI Safety & Evaluation
WWfh
REMOTE · WORLDWIDE
—
Full-time
STAFF
About the Role
This role involves leading the design and evaluation of safety mechanisms for foundation models, focusing on mitigating jailbreaks and prompt injection attacks, and developing red teaming workflows.
Responsibilities
- Design and build safety mechanisms for foundation models
- Evaluate model vulnerabilities to jailbreaks and prompt injection
- Develop red teaming workflows to assess model safety
Tech Stack
LLMGenerative AIAI Safety
W
Wfh
San Francisco · US · 8+ employees
WFH.team provides remote job intelligence for candidates and employers, offering confirmed remote job listings and resume-based matching. They also provide various employer-facing hiring tools and public resources for remote work workflows.
