Security Researcher, Agentic AI Threats

OpenAI OpenAI · AI Frontier · San Francisco, CA · Safety Systems

Research role focused on mitigating AI threats to global security, specifically by identifying and preparing for security threats from advanced internal AI agents. The role involves designing security controls and stress-testing defenses with AI agent evaluations.

What you'd actually do

  1. Identify paths by which capable future internal AI agents could compromise OpenAI.
  2. Design security controls - focusing on measures with long lead times that benefit from advanced preparation.
  3. Stress-test defenses with AI agent evaluations and penetration tests

Skills

Required

  • security
  • modern infrastructure
  • operating systems
  • cloud
  • containers
  • CI/CD
  • distributed systems
  • software engineering
  • building prototypes

Nice to have

  • securing cloud infrastructure
  • core components of the AI stack

What the JD emphasized

  • AI agent
  • security controls
  • AI agent evaluations

Other signals

  • AI agents
  • security threats
  • mitigation
  • preparedness framework