Researcher, Frontier Cybersecurity Risks

Overview

Researcher position focused on cybersecurity risks for frontier AI misuse prevention. You will help design and implement an end-to-end mitigation stack across OpenAI products.

What you'll do

• Design and implement prevention, monitoring, detection, and enforcement components for model-enabled cyber misuse.
• Integrate safeguards across product surfaces with product and engineering teams.
• Evaluate trade-offs across coverage, latency, model utility, and user privacy, and propose testable solutions.
• Collaborate with risk and threat modeling partners to align mitigation to attacker behaviors and misuse scenarios.
• Run rigorous testing and red-teaming to stress-test mitigations and iterate based on findings.

What you'll need

• Demonstrated experience in deep learning and transformer models.
• Proficiency with PyTorch or TensorFlow.
• Strong foundation in data structures, algorithms, and software engineering principles.
• Familiarity with training and fine-tuning large language models (distillation, supervised fine-tuning, policy optimization).
• Ability to work collaboratively with cross-functional teams across research, security, policy, product, and engineering.
• Significant experience designing and deploying technical safeguards for abuse prevention, detection, and enforcement at scale.

Nice to have

• Background knowledge in cybersecurity or adjacent fields.