Skip to content

About the role

The Post-Training team develops methods to make multimodal models adaptive and aligned with human intent. The researcher designs new techniques for preference optimization and model evaluation, exploring how feedback guides reasoning and building infrastructure to measure and improve model behaviors.

Our summary of the posting; the original is on the Cartesia 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.