Skip to content

About the role

The Safety Training team shapes model behavior through post-training and reinforcement learning methods. The researcher works on large training runs to teach models to assist with security tasks while preventing misuse. This involves studying model mistakes and improving future training runs based on findings.

Our summary of the posting; the original is on the OpenAI careers page.

What the posting requires

Required
Preferred

These tags are our reading of the posting. They can miss something; the original posting is the reference.

Add your resume

Drop a PDF here, or

PDF or plain text, up to 10 MB.

Nothing is kept until you say so.