Researcher, Agent Safety, Training and Evaluations
Where this listing came from
This job was taken from a public posting. Openai has not claimed the listing yet, so nobody there has committed to interviewing through VoxJobs yet — we interview you, we reach out to the company with the candidates, and you are told the moment they join.
About the role
About the Team
The Agent Safety team works to ensure that increasingly capable AI agents act safely, exercise sound judgment, and remain aligned with user intent. Our mission is to reduce the probability of severe unintended outcomes from increasingly capable AI agents while preserving their ability to act effectively and autonomously.
Our work spans three areas:
- Training: Create training methods, environments and data that teach agents to make better decisions in consequential situations. We turn real-world failures into training signals that prevent similar incidents, and identify precursor behaviors and mitigations to address emerging risks.
- Measurements: Build evaluations and production metrics that identify emerging risks and measure whether our interventions work.
- Oversight: Develop oversight and system mitigation mechanisms that reduce harmful actions while preserving useful autonomy (for example future versions of auto-review https://alignment.openai.com/auto-review/).
About the Role We’re looking for strong executors with excellent judgment, comfort with ambiguity, and an understanding of frontier model research. You don’t need prior safety or alignment experience, we also welcome people that recently realized that alignment and safety is a critical area to contribute to.