Researcher, Frontier Cybersecurity Risks
Core
Design and implement an end-to-end mitigation stack to reduce severe cyber misuse across OpenAI's products, focusing on prevention, monitoring, detection, and enforcement.
Role type
Researcher, Frontier Cybersecurity Risks
Builds
Safeguards for model-enabled cybersecurity misuse across product surfaces
Domain
AI Safety / Cybersecurity
Deliverable
production ML models
Required skills
deep learning, transformer models, PyTorch, TensorFlow, data structures, algorithms, software engineering principles, large language model training and fine-tuning, distillation, supervised fine-tuning, policy optimization, technical safeguards design and deployment at scale
Preferred skills
cybersecurity background knowledge
Technologies
PyTorch, TensorFlow
Responsibilities
Design and implement mitigation components for model-enabled cybersecurity misuse; Integrate safeguards across product surfaces in partnership with product and engineering teams; Evaluate technical trade-offs within the cybersecurity risk domain; Collaborate with risk and threat modeling partners to align mitigation design; Execute rigorous testing and red-teaming workflows to stress-test the mitigation stack
Seniority
Individual Contributor (IC), Research