jobs

Researcher, Frontier Cybersecurity Risks

About the teamModels are becoming increasingly capable—moving from tools that assist humans to agents that can plan, execute, and adapt in the real world. Mitigating the frontier risks resulting from these capabilities is paramount to OpenA

Company

OpenAI

Location

San Francisco

Status

Open

Posted

2026-08-03T21:35:27.89+00:00

OpenAI's Preparedness team is hiring a researcher to reduce severe cyber misuse of its products. The work covers prevention, monitoring, detection and enforcement: designing mitigation components, integrating safeguards across product surfaces with product and engineering teams, weighing trade-offs between coverage, latency, model utility and user privacy, and running testing and red-teaming against evolving attacks. The posting asks for deep learning and transformer experience, PyTorch or TensorFlow, knowledge of fine-tuning large language models, software engineering fundamentals, and experience deploying abuse-prevention safeguards at scale. Cybersecurity background is a plus.