Preference Model

Preference ModelPreference Model
Preference Model

Preference Model

Stealth modeStealth Mode

Preference Model is building the next generation of training data to power the future of AI by developing machine learning infrastructure software for reinforcement learning experimentation.

Website
2025Active17San Francisco, United States
Rate
Advertise here

About

Preference Model develops machine learning infrastructure software designed to support experimentation in reinforcement learning. They build high-quality RL training environments that reflect real-world complexity, with diverse tasks and robust reward functions, to teach models to perform ML research. The company partners with frontier AI labs to build capabilities for the next generation of LLMs.

Technology stack

detected 2026-07-12
CDN
Email
Hosting
Stack
Hiring
Languages
62
ML / AI
33
LLM / inference
6
GPU / CUDA
33
Cloud
Comments

No comments yet. Be the first to share your take.

Frequently asked

What does Preference Model do?

Preference Model develops machine learning infrastructure software designed to support experimentation in reinforcement learning. They build high-quality RL training environments that reflect real-world complexity, with diverse tasks and robust reward functions, to teach models to perform ML research. The company partners with frontier AI labs to build capabilities for the next generation of LLMs.

Where is Preference Model headquartered?

Preference Model is headquartered in San Francisco, United States.

When was Preference Model founded?

Preference Model was founded in 2025.

What industry does Preference Model operate in?

Preference Model operates in Reinforcement Learning, Reinforcement Learning from Human Feedback, Synthetic Data, Synthetic Data Generation, MLOps, Developer Tools.

How many employees does Preference Model have?

Preference Model has approximately 17 people on record.