Researcher, Agent Safety, Oversight and System Mitigations
$380k - $500k • San Francisco • FullTime
Posted 1mo ago
Job Location
San Francisco
Tech Stack
Remote Work Policy
On-site
Employment Type
FullTime
Categories
AI Agent Engineer
About the job
This role focuses on oversight and system-level mitigations to enable increasingly capable AI agents to operate safely and autonomously in real environments. The team prioritizes building oversight systems used in practice today, both internally and externally, and studies longer-term questions about how agent systems can be supervised, constrained, and corrected. We are looking for a safety-minded researcher or engineer who can reason rigorously about security boundaries and agent behavior, then build and test practical mitigations. A background in AI control or security is welcome but not required.
Responsibilities
- Design, build, and evaluate system-level controls for agent actions, such as agent-based review.
- Plan how controls fit into a broader system, including sandboxing with process isolation and permission boundaries.
- Work closely with a Codex harness engineering team to productionize AI controls.
- Red-team end-to-end agentic systems to measure whether controls prevent data exfiltration, unsafe tool use, and other harmful outcomes.
- Improve the safety-productivity tradeoff by measuring and reducing missed harmful actions, unnecessary blocks, approval burden, and latency.
Requirements
- Strong systems or security instincts with the ability to reason concretely about isolation boundaries, permissions, attack surfaces, and failure modes in complex systems.
- Ability to turn ambiguous safety questions into concrete threat models, reproducible experiments, and practical mitigations.
- Capacity to revise approaches based on evidence from deployment.
- Ability to build robust experimental infrastructure and design evaluations that distinguish promising mitigations from brittle ones.
- Deep interest in frontier AI alignment, safety, and control.
Benefits
- Hybrid work model (3 days in office per week)
- Relocation assistance for new employees