About this role
Scale AI is seeking a Research Scientist to focus on Agent Robustness within their Scale Labs team. This role involves researching fundamental challenges in building safe and aligned AI agents, designing and implementing testing harnesses, and developing mitigations for AI failure modes. The position is ideal for individuals passionate about advancing AI safety and contributing to trustworthy AI deployments.
What we are looking for 6
- Research AI agent capabilities, safety, and risk factors
- Design and build harnesses to test AI agent behavior
- Develop exploits and mitigations for AI failure modes
- Characterize and mitigate risks in multi-agent systems
- Experience with post-training and RL techniques (RLHF, DPO)
- Track record of published research in machine learning, particularly generative AI