Principal Research Scientist - Evaluations
CanvaSan FranciscoFull TimeEngineering
Remotely
llmbenchmarkingevaluationtransformersvlmsrlhfmultimodalrlaif
Job Description
📋 Description
- Establish the evaluation gates that inform launch decisions, and be accountable for the judgement
- Diagnose anomalous evaluation results during production training runs, separate model regressions
- Partner with Design Generation, Foundation Models and Agents teams so evaluation shapes their
- Work directly with designers, creators and product teams to turn subjective creative judgement into
- Mentor senior research scientists and engineers, and raise the bar for evaluation craft across the
🎯 Requirements
- A track record of defining evaluation frameworks and standards from the ground up rather than
- Experience linking evaluation metrics to downstream business or user outcomes, and diagnosing why
- Experience turning subjective human judgement into reliable, objective evaluation signal through
- Strong grounding in multimodal generative models (diffusion, transformers, VLMs and MLLMs) and
- Experience with reward modelling, preference learning, or alignment methods involving human feedback
- Experience setting technical direction across multiple teams or a wide specialty area in a globally
🎁 Benefits
- Equity packages - we want our success to be yours too
- Health benefits plans to support you and your wellbeing
- 401(k) retirement plan with company contribution
- Inclusive parental leave policy that supports all parents & carers
- An annual Vibe & Thrive allowance to support your wellbeing, social connection, office setup
Back to all jobs