About the role
About the Team
Models are becoming increasingly capable—moving from tools that assist humans to agents that can plan, execute, and adapt in the real world. Mitigating the frontier risks resulting from these capabilities is paramount to OpenAI’s ability to continue deploying models safely.
The Preparedness team is dedicated to addressing these critical risks. Our work includes:
- Measurement. Monitoring and predicting the evolving capabilities of frontier AI systems.
- Mitigation. Keeping misalignment safeguards, alignment tools, and on track to adequately address extreme threats that might arise in the future.
- Coordination. Setting mitigation targets by maintaining OpenAI’s preparedness framework https://openai.com/index/updating-our-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
We’re looking for a very senior, independent Software Engineer to lead the technical work behind cyber safeguard infrastructure in Preparedness. You’ll bring production-grade engineering discipline to systems that support everything from cyber evaluations and safeguard research internally to enabling the safe deployment of capabilities externally, while working closely with researchers and security partners. The right person can move comfortably from ambiguous research needs to robust, operable systems—and can drive the work across organizational boundaries with clear communication.
In this role, you’ll
- Drive the technical direction and hands-on execution for cyber safeguard infrastructure.
- Establish production-quality reliability, observability, on-call, and SLA/SLO practices.
- Partner with teams across the company - security, research, policy and product - to translate evolving needs into durable platforms.
- Lead cross-functional technical work, create alignment, and unblock collaborators.
- Build reliable systems that support cyber evaluations and research workflows.
- Improve the scalability, usability, and operational safety of cyber safeguards.
- Mentor teammates and raise the engineering bar while remaining deeply hands-on.
You might thrive in this role if you have:
- Extensive experience owning large-scale production systems, including reliability, on-call, incident response, SLAs/SLOs, and operational excellence.