Researcher, Frontier Cybersecurity Risks

📋 Description

• Design and implement mitigation components for model-enabled cybersecurity misuse—spanning
• Integrate safeguards across product surfaces in partnership with product and engineering teams to
• Evaluate trade-offs in cybersecurity risk design (coverage, latency, model utility, privacy) and
• Collaborate with risk and threat modeling partners to align mitigation with attacker behaviors and
• Execute rigorous testing and red-teaming workflows to stress-test the mitigation stack across

🎯 Requirements

• Experience in deep learning and transformer models.
• Proficiency with PyTorch or TensorFlow.
• Strong foundations in data structures, algorithms, and software engineering.
• Familiarity with training/fine-tuning large language models (distillation, supervised fine-tuning
• Ability to work cross-functionally with research, security, policy, product, and engineering teams.

🎁 Benefits

• Equity compensation as part of total rewards.
• Opportunity to work on high-impact safety research for OpenAI products.