scout22 › Jobs › Cartesia › Researcher, Evals

Researcher, Evals

Cartesia

Mid levelOn-site*HQ - San Francisco, CA

Shape how AI models are evaluated.

Apply in one tap on the scout22 app — your details fill themselves in on every application Apply on Cartesia's website fill out every field yourself, every time

Already have scout22? Open this job in the app

About Cartesia

Cartesia is pioneering AI that learns and interacts like humans.

What you'd do

Identify key model capabilities for evaluation
Develop and implement evaluation pipelines
Partner with research teams for model development
Prototype user studies and behavioral experiments

What they're looking for

Experience with evaluation frameworks for generative models
Strong technical and analytical skills
Creativity in defining quantitative metrics
Excitement for building evaluation systems

Perks

Competitive base salary and equity
Fully covered health insurance
Flexible PTO policy and meals provided