jobs

Researcher, Alignment

About the TeamThe Alignment team at OpenAI is dedicated to ensuring that our AI systems are safe, trustworthy, and consistently aligned with human values, even as they scale in complexity and capability. Our work is at the cutting edge of A

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2024-08-27T16:33:01.117+00:00

OpenAI's Alignment team is hiring a researcher to design and run experiments that keep AI systems following human intent as capabilities grow. Work includes building evaluations for risks and alignment, studying how alignment scales with compute, data and context, training models to be calibrated on correctness and risk, and developing scalable oversight and human-AI interaction methods. The posting seeks a PhD or equivalent, strong engineering skills in large-scale ML systems such as PyTorch, and interface work in TypeScript or Python. Based in San Francisco or London.