Stanford AI Oversight project recruits postdocs to audit black-box agentic AI systems

LesterMackey · x · 2026-11-20

The Stanford Collaboration on AI Oversight is recruiting postdocs for its interdisciplinary effort on adaptive monitoring, auditing, and intervention policies for black-box agentic AI systems. Combining statistics, ML, RL, incentive design, and causal inference, the project spans AI evaluation, selective human oversight, and responsible deployment (safety contracts). Published work includes "Knowing When to Intervene: Causal Evaluation of AI Agents" and "Reliable AI-Assisted Decisions via Selective Auditing." The team is also building an open-source AI Safety Harness to monitor agent activity, support intervention (continue, redirect, stop, or escalate to humans), and improve oversight from feedback.

Original post →

More from Safety

Safety channel →