Abuse Investigator (AI Self-Improvement Risk)

Tech Stack

Responsibilities

• Review leads, investigate model behavior, and identify cases where systems demonstrate agentic or autonomous patterns that introduce safety risks
• Detect and analyze behaviors such as multi-step planning, capability chaining, tool use, persistence, and workaround behavior
• Develop signals and tracking strategies to help proactively identify emerging agentic risk patterns across our platform
• Identify gaps in existing safeguards, evaluations, or monitoring systems and propose improvements
• Communicate investigation findings clearly to technical, policy, and leadership stakeholders

Culture

Requirements