jobs

Research Scientist, Alignment

OpenAI is seeking a Research Scientist to join our Alignment team. You will develop and run experiments to understand how to make language models safe, honest, and corrigible. This role requires deep expertise in machine learning, strong ma

In inglese

Company

OpenAI

Location

San Francisco, CA

Status

Closed

Posted

2026-02-01T00:00:00+00:00

OpenAI's Alignment team is hiring a full-time research scientist in San Francisco, with hybrid work. The role centers on designing and running experiments that probe whether language models can be made safe, honest and corrigible, and on turning that work into practical changes to deployed models alongside safety and policy colleagues. The posting asks for deep machine-learning knowledge, solid mathematical grounding, and real interest in aligning AI systems with human values. Pay is listed at 240,000 to 340,000 USD.