Principal Research Scientist - Evaluations

📋 Description

• Establish evaluation gates for Canva Research across design, image, video, audio and agentic
• Diagnose anomalous evaluation results during production training; separate model regressions from
• Collaborate with Design Generation, Foundation Models and Agents teams to shape training and
• Turn subjective creative judgement into measurable criteria with designers, creators and product
• Mentor senior researchers and engineers; elevate evaluation craft across the group.
• Represent Canva's evaluation vision to senior leadership and industry when valuable.

🎯 Requirements

• Strong track record defining evaluation frameworks and standards at scale, ideally in GenAI.
• Experience linking evaluation metrics to downstream business or user outcomes; diagnose divergences.
• Ability to translate subjective human judgement into reliable evaluation signals via rubric design
• Deep grounding in multimodal generative models (diffusion, transformers, VLMs, MLLMs) and
• Experience with reward modelling, preference learning, or alignment methods involving human
• Experience setting technical direction across multiple teams in a global org; proactive ownership

🎁 Benefits

• Equity packages; inclusive parental leave; Thrive/wellbeing allowance; flexible leave options.
• Recognized Canva Life benefits and a supportive, global team culture.