AI Red Teamer

TL;DR

AI Red Teamer (AI/Security): Developing and executing adversarial test suites for LLMs and multimodal models with an accent on identifying policy edge cases and security vulnerabilities. Focus on crafting complex jailbreaks, analyzing model outputs, and documenting findings to enhance the safety of frontier AI systems.

Location: Must be based in the U.S.

Salary: $70,000–$90,000

Company

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

What you will do

• Develop and run manual and scripted adversarial test suites for LLMs and image/video models.
• Craft multilingual prompts, jailbreaks, and escalation chains targeting policy edge cases.
• Analyze model outputs, triage failures, and write concise vulnerability reports.
• Contribute to internal tooling including prompt libraries, scenario generators, and dashboards.

Requirements

• Must be based in the U.S.
• 2-4 years of experience in red-teaming, security research, or trust & safety.
• Basic proficiency with Python and command-line tools.
• Demonstrated interest in AI safety, adversarial ML, or abuse detection.
• Strong writing skills for vulnerability reports and long-form analyses.
• Ability to rapidly context switch across domains and modalities.

Nice to have

• Full professional proficiency in Arabic, Chinese, Farsi, Portuguese, Russian, or Spanish.
• Prior work in content moderation, disinformation analysis, or cyber-threat intelligence.
• Experience with prompt-automation frameworks like Promptfoo, LangChain, or Garak.
• Familiarity with vector search or LLM fine-tuning workflows.
• Formal training or certification in red-teaming or penetration testing.

Culture & Benefits

• Fully remote work environment with flexible hours.
• Comprehensive health, dental, and vision insurance.
• 401(k) retirement plan.
• Generous PTO and paid holidays.
• Professional-development stipend for courses, conferences, or language study.