Red Teaming Fellow (AI)

TL;DR

Red Teaming Fellow (AI): Evaluating the safety, security, and reliability of advanced AI systems through adversarial testing and vulnerability research. Focus on identifying failure modes, designing attack strategies, and documenting actionable insights to ensure the safe deployment of frontier models.

Location: Must be based in the continental U.S.

Salary: $25/hour (undergraduate) to $32.50/hour (graduate)

Company

hirify.global provides safety and threat-intelligence layers for frontier AI labs, unicorns, and global technology platforms.

What you will do

• Conduct adversarial testing of AI systems across safety, security, and misuse scenarios.
• Design and execute red teaming exercises against models, agents, and AI-enabled applications.
• Develop prompts, attack strategies, and test cases to identify vulnerabilities and failure modes.
• Analyze model behavior and document findings in clear, actionable reports.
• Support the development of evaluation frameworks, taxonomies, and testing methodologies.
• Research emerging AI threats, attack techniques, and risk trends.

Requirements

• Must be based in the continental U.S.
• Pursuing or recently completed a degree in Computer Science, Cybersecurity, Engineering, Data Science, Mathematics, Political Science, International Relations, or a related field.
• Strong interest in AI safety, cybersecurity, red teaming, or adversarial testing.
• Familiarity with AI abuse including jailbreaking, system prompt extraction, indirect prompt injection, and data exfiltration.
• Ability to think creatively from an adversarial perspective.
• Experience with Python, Bash, large language models, or research methodologies.

Culture & Benefits

• Flexible start and end dates.
• Remote work environment.
• Flexible schedule, up to 20 hours per week.