Description
We are looking for a researcher to develop and test new methods for securing frontier AI systems. You will investigate open-ended questions about model behavior, containment, and safeguards,designing experiments, building evaluations, and developing defenses where established approaches may be insufficient.
Responsibilities:
- Design and run experiments using frontier models and hands-on security techniques to discover failure modes in sandboxes, research infrastructure, and the services models can reach.
- Develop threat models and novel adversarial tests for attacks that cross multiple security boundaries.
- Invent, prototype, and evaluate defenses that strengthen isolation and limit the impact of a compromised boundary.
- Develop and red-team model-based safeguards and monitors of model reasoning and actions.
- Develop automated adversarial tests and repeatable evaluations to measure progress as model capabilities, configurations, and attack strategies change.
- Partner across Research, Security, and infrastructure teams to prioritize risks and turn findings into deployed improvements.
Requirements:
- Hands-on experience conducting research with large language models.
- Ability to turn an open-ended question into a clear hypothesis and build reproducible experiments.
- Practical security experience relevant to this work, such as sandboxing, vulnerability research, or detection and monitoring.
- Experience with operating systems, containers or virtualization, distributed infrastructure, or AI agents would also be valuable.
For more fresh new jobs, check out yubhub.co.