Cartesia
Researcher, Evals
$220K–$350K
*HQ - San Francisco, CA · On-site · Full-time · Posted Oct 21, 2025
- Visa sponsorship
- Visa sponsorship support is assessed case by case and depends on the role and work location; sponsorship is not guaranteed.
About the job
Designs evaluation frameworks, metrics, pipelines, and user studies to measure how AI models reason, remember, and interact in real-world use.
What you'll do
- Define model capabilities and behaviors for next-generation evaluations.
- Develop evaluation pipelines with statistical analysis and clear reporting, and integrate them into model development.
- Prototype user studies and behavioral experiments grounded in real-world use.
What they ask for
- Experience designing or implementing evaluation frameworks for generative models (audio, text, or multimodal).
- Strong technical and analytical skills, including translating research ideas into production-ready systems.
- Ability to create quantitative metrics for subjective or behavioral qualities.
Nice to have
- Understanding of model alignment concepts and evaluation approaches.
Pay
$220K – $350K (base salary)
AI focus
Evaluates generative models and interactive machine intelligence, including reasoning, memory, and behavior over time.
Model-written summary · the original posting is authoritative