Jobs

Scale Labs is seeking a Research Scientist specializing in Agent Robustness to join their new policy research team. This role focuses on the fundamental challenges of building safe and human-aligned AI agents, including researching capabilities, designing testing harnesses for harmful actions, and mitigating failure modes. The ideal candidate will have practical experience in collaborative technical research, expertise in post-training and RL techniques, and a track record of published research in generative AI. This position offers an exciting opportunity to shape the future of AI safety and contribute to understanding and mitigating AI risks.