Preference Model
Backed by
Preference Model is a superintelligence data research company. Almost every aspect of how a model behaves is shaped by the reward signals it's trained on. That's why we're building RL environments for training capable, better-aligned superintelligences.
Member of Technical Staff - ML Platform Engineer
Member of Technical Staff - Research Engineer, Post-training
Member of Technical Staff - AI/ML Infrastructure Engineer, RL Post-training
Member of Technical Staff - Research Engineer, RL Environments
