RL environments for automating ML research and engineering

Preference Model Raises $16M Seed

Member of Technical Staff - AI/ML Infrastructure Engineer, RL Post-training

Preference Model is a superintelligence data research company building RL environments for training capable, better-aligned AI systems. The Senior ML Infrastructure Engineer builds and scales compute, scheduling, data, tooling, and evaluation infrastructure that enables high-throughput post-training research on large language models.

Member of Technical Staff - Research Engineer, Post-training

Preference Model is a superintelligence data research company building reinforcement learning environments for training capable, better-aligned AI systems. The Research Engineer will advance post-training for large language models by implementing novel approaches, building and optimizing RL infrastructure, and shaping research directions.

Preference Model is building automated machine learning research engineering focused on creating reinforcement learning environments for real-world tasks. The Research Engineer will advance post-training for large language models by implementing novel approaches, training and evaluating models, designing RL environments and evaluations, and optimizing distributed training infrastructure.