Frontier AI Cyber Risk Researcher

OpenAI; San Francisco (CA); On-site; USD 295,000 - 445,000; Full time

Job summary

A leading AI research organization is seeking a Researcher to focus on cybersecurity risks. The role involves designing and implementing mitigation strategies across products, ensuring effective safeguards as AI capabilities develop. Ideal candidates should have deep learning experience, knowledge of cybersecurity, and the ability to collaborate across various teams. The compensation range is competitive, reflecting the importance of this role within the organization.

Qualifications

• Experience in designing and deploying technical safeguards for abuse prevention.
• Familiarity with methods for training large language models.
• Passion for AI safety and real-world application.

Responsibilities

• Design and implement mitigation components for cybersecurity misuse.
• Integrate safeguards across product surfaces.
• Evaluate technical trade-offs and propose viable solutions.

Skills

Deep learning and transformer models

Knowledge of cybersecurity principles

Frameworks like PyTorch or TensorFlow

Data structures and algorithms

Collaboration with cross-functional teams

Job description

A leading AI research organization is seeking a Researcher to focus on cybersecurity risks. The role involves designing and implementing mitigation strategies across products, ensuring effective safeguards as AI capabilities develop. Ideal candidates should have deep learning experience, knowledge of cybersecurity, and the ability to collaborate across various teams. The compensation range is competitive, reflecting the importance of this role within the organization.