Offensive Security Engineer, Preparedness

About the team

Frontier AI models have the potential to benefit all of humanity but also pose increasingly severe risks. To ensure that AI promotes positive change, we have dedicated a team to help us best prepare for the development of increasingly capable frontier AI models. This team, Preparedness, reports directly to our CTO and is tasked with identifying, tracking, and preparing for catastrophic risks related to frontier AI models.

Specifically, the mission of the Preparedness team is to:

• Closely monitor and predict the evolving capabilities of frontier AI systems, with an eye towards misuse risks whose impact could be catastrophic (not necessarily existential) to our society and ensure we have concrete procedures, infrastructure, and partnerships to mitigate these risks and, more broadly, to handle the development of powerful AI systems safely.

Our team will tightly connect capability assessment, evaluations, internal red teaming for frontier models, and overall coordination on AGI preparedness. The team’s core goal is to ensure that we have the infrastructure needed for the safety of highly capable AI systems—from the models we develop in the near future to those with AGI-level capabilities. 

About the role:

We are looking to hire an exceptional offensive security engineer to push the boundaries of our frontier models. We are looking for those with an expert grasp of offensive security, AI safety concerns, and how our frontier models will shape offensive security capabilities.

In this role, you will:

• Work on identifying offensive security capabilities present in frontier models, and how they might assist with adversarial cybersecurity operations.
• Assist in building and refining evaluations of frontier AI models that assess the extent of these identified risks.
• Build scalable systems and processes to support these evaluations.
• Contribute to the refinement of risk management and the overall development of "best practice" guidelines for AI safety evaluations

You might thrive in this role if you are:

• Passionate and knowledgeable about short-term and long-term AI safety risks.
• An expert in modern adversary tactics and vulnerability research
• Knowledgeable about exploit development and reverse engineering techniques
• Have experience leading red-team and penetration testing engagements
• Be able to translate your cybersecurity expertise and any findings to research engineers building capability evaluations.

It would be great if you also have:

• Experience in ML research engineering, ML observability and monitoring, creating large language model-enabled applications, or another technical domain applicable to AI risk
• A good understanding of the (nuances of) societal aspects of AI deployment