Researcher, Automated Red Teaming

Responsibilities

• Own the research and technical direction for automated red teaming across catastrophic risk areas, including classifier jailbreak discovery and bio threat-development elicitation.
• Build scalable, research-driven systems that continuously uncover failure modes in models and safeguards.
• Partner with vertical risk teams (Cyber, Bio, Loss of Control) to define threat models and prioritize targets.
• Collaborate with the Classifiers team to translate discovered attacks into training data, evaluations, and measurable robustness gains.
• Work with Product, Engineering, and Safety stakeholders to ensure automated red teaming outputs are operationally useful.

Requirements

• Strong applied research instincts, particularly regarding the design of reproducible and interpretable experiments.
• Hands-on experience with LLMs and agents, including multi-turn behaviors and tool use.
• Proven ability to build scalable automation and production-adjacent pipelines rather than just prototypes.
• Solid software engineering fundamentals, including data structures, algorithms, and testing discipline.
• Expertise in threat modeling and the ability to think from an attacker's perspective.
• Excellent communication skills to translate complex findings into actionable insights for diverse stakeholders.

Preferred Qualifications

• Experience in adversarial machine learning or security research.
• Background in red teaming, abuse prevention systems, or large-scale evaluation infrastructure.

Benefits

• Competitive base salary with generous equity and performance-related bonuses.
• Comprehensive medical, dental, and vision insurance.
• 401(k) retirement plan with employer match.
• Flexible paid time off and paid parental leave.
• Daily meals in the office and mental health support.
• Annual learning and development stipend.

About the Company

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. We push the boundaries of AI capabilities and seek to safely deploy them to the world through our products.