Researcher, Frontier Cybersecurity Risks

What this role involves

OpenAI is hiring a Researcher for Frontier Cybersecurity Risks to join the Preparedness team. The role involves designing and implementing mitigation components for model-enabled cybersecurity misuse, integrating safeguards across products, and collaborating with cross-functional teams. Candidates should have experience with deep learning, transformer models, and frameworks like PyTorch or TensorFlow.

Skills this posting asks for

• deep learning
• transformer models
• pytorch
• tensorflow
• data structures
• algorithms
• software engineering
• large language models
• distillation
• supervised fine-tuning
• policy optimization
• abuse prevention
• detection
• enforcement
• cybersecurity

From the employer’s posting

ABOUT THE TEAM Preparedness is a critical Safety Research team at OpenAI, which is focused on mitigating AI threats to global security https://openai.com/index/updating-our-preparedness-framework/ that could scale to an extreme level of severity. Our work involves: 1. Measurement. Monitoring an…