Scale - Research and Development, On-site work

Scale AI seeks a Research Scientist for Safety Post Training to bridge AI research and policy. You'll develop post-training methods (RLHF, DPO, GRPO) and interpretability techniques to enhance frontier model safety. Collaborate with policymakers and engineers in San Francisco or New York, transla...

Join our team as a Research Scientist focused on Agent Robustness in San Francisco or New York. You will tackle fundamental challenges in building safe, aligned AI agents, leveraging RLHF, DPO, and agent evaluation. We seek a published ML researcher with 3+ years of experience in sophisticated pr...