Description
OpenAI is hiring a Researcher for cybersecurity risks to design and implement an end-to-end mitigation stack that reduces severe cyber misuse across its products. The role covers prevention, monitoring, detection, enforcement, cross-functional integration, technical trade-offs, threat modeling, and rigorous testing and red-teaming. Candidates should have deep learning and transformer-model experience, proficiency with PyTorch or TensorFlow, software engineering fundamentals, large-language-model training knowledge, and significant experience deploying technical safeguards at scale.
