Researcher, Frontier Cybersecurity Risks

Details

Preparedness is a critical Safety Research team focused on mitigating AI threats to global security that could scale to an extreme level of severity. The team works across measurement, mitigation, and coordination by monitoring frontier AI capabilities, maintaining safeguards and security measures, and setting mitigation targets through OpenAI's preparedness framework.

Models are becoming increasingly capable of planning, executing, and adapting in the real world. As OpenAI works toward AGI, cybersecurity is an important frontier because the same systems that accelerate productivity can also accelerate exploitation.

As a Researcher for cybersecurity risks, you will help design and implement an end-to-end mitigation stack to reduce severe cyber misuse across OpenAI's products. You will contribute to building safeguards that are enforceable, scalable, effective, and robust as products, model capabilities, and attacker behaviors evolve.

Responsibilities

• Design and implement mitigation components for model-enabled cybersecurity misuse, spanning prevention, monitoring, detection, and enforcement, under the guidance of senior technical and risk leadership.
• Integrate safeguards across product surfaces in partnership with product and engineering teams, ensuring protections are consistent, low-latency, and able to scale with usage and new model capabilities.
• Evaluate technical trade-offs in cybersecurity risk, including coverage, latency, model utility, and user privacy, and propose pragmatic, testable solutions.
• Collaborate with risk and threat-modeling partners to align mitigation design with anticipated attacker behaviors and high-impact misuse scenarios.
• Execute rigorous testing and red-teaming workflows to stress-test the mitigation stack against evolving threats, including novel exploits, tool-use chains, and automated attack workflows across different product surfaces.
• Iterate on mitigation systems based on testing and red-team findings.

Requirements

• Passion for AI safety and motivation to make cutting-edge AI models safer for real-world use.
• Demonstrated experience with deep learning and transformer models.
• Proficiency with frameworks such as PyTorch or TensorFlow.
• Strong foundation in data structures, algorithms, and software engineering principles.
• Familiarity with training and fine-tuning large language models, including distillation, supervised fine-tuning, and policy optimization.
• Ability to collaborate effectively 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.
• Background knowledge in cybersecurity or adjacent fields is a nice-to-have.

About OpenAI

OpenAI is an AI research and deployment company dedicated to ensuring that general-purpose artificial intelligence benefits all of humanity. The company develops AI systems and seeks to safely deploy them through its products.

OpenAI is an equal opportunity employer and does 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 characteristics. Background checks are administered in accordance with applicable law. OpenAI is committed to providing reasonable accommodations to applicants with disabilities.