Member of Technical Staff, Post-Training Research

You'll invent new ways to detect and scale the data that makes frontier AI models smarter. As frontier models continue to improve, model capability is increasingly driven by the quality of training data. You'll develop scalable systems that generate, curate, and improve high-quality supervision across coding, multimodal, and agentic tasks.

In this role, you also have an opportunity to be forward-deployed should it interest you, and work directly with the researchers at frontier labs to creatively scale new model capability strategies for improvement.

• Train and improve preference, reward, and ranking models from millions of human interactions
• Develop infrastructure for large-scale experimentation, model training, and specialize in online evaluation techniques
• Design systems that transform human preference data into reliable signals for downstream model evaluation and training