The opportunity
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…
What you'll do
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 agent autonomy (for example future versions of auto-review ).
Design, build, and evaluate system-level controls for agent actions like: agent-based review. Plan how they fit in a broader system including sandboxing with process isolation and permission boundaries.
Work closely with a Codex harness engineering team to productionize the AI controls.
Red-team end-to-end agentic systems to measure whether controls prevent data: exfiltration, unsafe tool use, and other harmful outcomes.
What they're looking for
- Improve the safety–productivity tradeoff by measuring and reducing missed: harmful actions, unnecessary blocks, approval burden, and latency.
- Have strong systems or security instincts and can reason concretely about: isolation boundaries, permissions, attack surfaces, and failure modes in complex systems.
- Enjoy turning ambiguous safety questions into concrete threat models,: reproducible experiments, and practical mitigations, and revising your approach based on evidence from deployment.
- Can build robust experimental infrastructure and design evaluations that: distinguish promising mitigations from brittle ones.
