← All roles

Researcher, Evals

Cartesia· Research
Apply on company site
*HQ - San Francisco, CA$220k - $350kFull-timePosted 11mo ago

About the role

Evaluations Lead who designs evaluation frameworks and pipelines for next-generation interactive AI models, bridging research, product, and infrastructure to measure capabilities, reasoning, memory, and real-world interaction.

Responsibilities

  • Identify and define key model capabilities and behaviors that matter for next-generation model evals
  • Develop and implement new evaluation pipelines with robust statistical analysis and clear reporting
  • Partner closely with model training and research teams to embed evaluation systems directly into model development loops
  • Prototype new user studies and behavioral experiments to ground evaluations in real-world use.

Qualifications

  • Experience designing or implementing evaluation frameworks for generative models (audio, text, or multimodal)
  • Strong technical and analytical skills, ability to translate open-ended research ideas into production-ready systems
  • Creativity in defining novel quantitative metrics for subjective or behavioral qualities
  • Excitement for building evaluation systems that bridge research and real-world use
  • Curiosity and rigor in equal measure; motivation driven by discovering how to measure meaningful progress in intelligent behavior

Skills

Required:Evaluation framework designProduction-ready systemsQuantitative metrics designCross-functional collaboration

Benefits

  • Compensation: Competitive base salary alongside attractive equity package
  • Health Insurance: Fully covered medical insurance along with dental and vision for you and your family
  • Parental Leave: 9 weeks paternity & 12 weeks maternity leave
  • 401(k)
  • Commuter Allowance: Monthly stipend to help you get to and from the office
  • Flexible PTO
  • Meals & Snacks: Lunch, dinner and plenty of snacks, provided daily
Last updated Jul 15, 2026. Interested? Apply on the company site.

About Cartesia

Real-time TTS API with AI laughter and emotion

Cartesia offers Sonic-3, a streaming text-to-speech API capable of generating natural, expressive voices with laughter in 40+ languages—built for AI agents and interactive applications.

AI voicesinteractive appsliquid-ai-recruiting-targetmultilingualstreaming APItext-to-speechvoice-ai-stack
Company profileWebsite

More open roles at Cartesia