Researcher, Misalignment Research

📋 Description

• Design and implement worst-case demonstrations that reveal AGI alignment risks.
• Develop adversarial and system-level evaluations grounded in those demonstrations.
• Create automated tools and infrastructure to scale automated red-teaming and stress testing.
• Research failure modes of alignment techniques and propose improvements.
• Publish papers that shift safety strategy or industry practice.
• Partner with engineering, research, policy, and legal teams to integrate findings into safeguards and governance processes.

🎯 Requirements

• 4+ years in AI red-teaming, security research, adversarial ML, or related safety fields.
• Strong research track record: publications, open-source projects, or high-impact internal work.
• Fluent in modern ML/AI techniques; comfortable hacking on large-scale codebases and eval infra.
• Clear communication with technical and non-technical audiences; translate findings into actionable recommendations.
• Ability to drive cross-functional projects spanning research, engineering, and policy.
• PhD or masters in CS/ML/security or equivalent (nice to have but not required).

🎁 Benefits

• Equal opportunity employer; diverse perspectives welcomed.
• Reasonable accommodations for applicants with disabilities.
• OpenAI privacy policy and data protections.
• Background checks and compliance with applicable laws.