Intelligence Analyst for AI Red Teaming

Intelligence Experts apply operational, analytic, and tactical experience to simulate and assess how malicious actors could use large language models to plan, enable, or enhance violent acts, terrorism, targeted assassinations, special operations, or tactical-level attacks. The role centers on using subject-matter expertise to identify and evaluate real-world threats posed by LLM outputs.

• Simulate scenarios in which adversaries might leverage LLMs to plan or improve acts of violence, terrorism, targeted assassinations, special operations, or tactical-level attacks.
• Conduct red teaming exercises focused on adversarial prompts and jailbreaking attempts against LLMs.
• Evaluate and interpret LLM-generated outputs from those exercises, assessing plausibility, operational utility, and whether outputs represent credible, material threats in real-world contexts.

• Bachelor''s, Master''s, or PhD degree, with relevant academic or professional preparation.
• Substantial experience in intelligence, defense, cyber operations, counterintelligence, counterterrorism, or closely related fields.
• Demonstrated operational or analytic background, preferably including experience with adversarial testing, red teaming, or threat assessment.

• Location: Remote.
• Employment type: Part-time.

Up to $200/hr (depending on the project)

This role is suited to professionals with government or military backgrounds who want to apply their expertise to anticipate national security risks from AI. When applying, provide a resume or CV and a brief summary of relevant operational, analytic, or tactical experience; emphasize roles or projects that involved planning, threat analysis, counteroperations, or adversarial assessments.