Researcher, Automated Red Teaming

About the team Preparedness is a critical Safety Research team at OpenAI, which is focused on mitigating AI threats to global security that could scale to an extreme level of severity. Our work involves: - Measurement. Monitoring and predicting the evolving capabilities of frontier AI systems. - Mitigation. Keeping misuse safeguards, alignment tools, and security measures on track to adequately address extreme threats that might arise in the future. - Coordination. Setting mitigation targets by maintaining OpenAI’s preparedness framework, and partnering with other staff to achieve these targets. This is urgent, fast-paced work that has far-reaching implications for the company and for society. About the role This role leads the Automated Red Teaming (ART) effort: building scalable, research-driven systems that continuously uncover failure modes in our models and safeguards, and translate those findings into actionable, production-facing improvements. The goal is to reduce expected harm by finding the highest-leverage, least-covered weaknesses early and reliably. In this role, you'll: - Own the research and technical direction for automated red teaming across catastrophic risk areas, with an initial emphasis on: - Automated classifier jailbreak discovery (cyber and bio). - Automated bio threat-development elicitation (worst-feasible planning uplift). - CoT monitoring evasion probing (and adjacent loss-of-control evaluations). - Partner closely with: - Vertical risk teams (Cyber, Bio, Loss of Control) to define threat models, prioritize targets, and land mitigations. - The Classifiers team to turn discovered attacks into training data, evals, and measurable robustness gains. - Product / Engineering / Safety stakeholders to ensure ART outputs are operationally useful. You might thrive in this role if you: - Feel a strong pull toward AI safety, and you’re motivated by reducing real-world catastrophic risk (not just publishing cool results). - Love breaking systems (responsibly) — you get energy from finding weird, high-severity failure modes and turning them into concrete fixes. - Have strong applied research instincts, especially around evaluations: you’re good at designing experiments that are reproducible, interpretable, and hard to fool. - Bring hands-on experience with LLMs and agents, including multi-turn behaviors, tool use, and the ways models adapt to constraints. - Are comfortable building scalable automation, not just prototypes — you can turn red-teaming ideas into pipelines that run continuously and produce high-signal outputs. - Have solid software engineering fundamentals (data structures, algorithms, testing discipline) and you can work effectively in a production-adjacent environment. - Think in threat models and incentives, and you naturally ask “what would an attacker do next?” or “how would this fail under pressure?” - Can translate messy findings into action, communicating clearly with researchers, engineers, product, and policy — and driving alignment on what to fix first. - Care about efficiency and prioritization, and you’re happy to say “no” to low-leverage work to focus on what moves the risk needle. - Nice to have: - Experience in adversarial ML, security research / red teaming, abuse prevention systems, or large-scale eval infrastructure. About OpenAI 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 the capabilities of AI systems and seek to safely deploy them to the world through our products. AI is an extremely powerful tool that must be created with safety and human needs at its core, and to achieve our mission, we must encompass and value the many different perspectives, voices, and experiences that form the full spectrum of humanity. We are an equal opportunity employer, and we do not discriminate on the basis of race, religion, color, national origin, sex, sexual orientation, age, veteran status, disability, genetic information, or other applicable legally protected characteristic. For additional information, please see OpenAI’s Affirmative Action and Equal Employment Opportunity Policy Statement. Background checks for applicants will be administered in accordance with applicable law, and qualified applicants with arrest or conviction records will be considered for employment consistent with those laws, including the San Francisco Fair Chance Ordinance, the Los Angeles County Fair Chance Ordinance for Employers, and the California Fair Chance Act, for US-based candidates. For unincorporated Los Angeles County workers: we reasonably believe that criminal history may have a direct, adverse and negative relationship with the following job duties, potentially resulting in the withdrawal of a conditional offer of employment: protect computer hardware entrusted to you from theft, loss or damage; return all computer hardware in your possession

Hands-on experience with LLMs and agents, including multi-turn behaviors, tool use, and the ways models adapt to constraints. Comfortable building scalable automation, turning red-teaming ideas into pipelines that run continuously and produce high-signal outputs. Solid software engineering fundamentals (data structures, algorithms, testing discipline) and the ability to work effectively in a production-adjacent environment. Ability to think in threat models and incentives, asking what an attacker would do next and how things would fail under pressure. Ability to translate messy findings into action and communicate clearly with researchers, engineers, product, and policy to drive alignment on what to fix first. Strong applied research instincts, especially around evaluations: designing experiments that are reproducible, interpretable, and hard to fool. Passion for AI safety and reducing real-world catastrophic risk. Nice to have: experience in adversarial ML, security research / red teaming, abuse prevention systems, or large-scale eval infrastructure.

Own the research and technical direction for automated red teaming across catastrophic risk areas, with initial emphasis on: Automated classifier jailbreak discovery (cyber and bio); Automated bio threat-development elicitation (worst-feasible planning uplift); CoT monitoring evasion probing (and adjacent loss-of-control evaluations). Partner closely with vertical risk teams (Cyber, Bio, Loss of Control) to define threat models, prioritize targets, and land mitigations. Collaborate with the Classifiers team to turn discovered attacks into training data, evaluations, and measurable robustness gains. Work with Product / Engineering / Safety stakeholders to ensure ART outputs are operationally useful.