Ai Red Teamer

10alabs

Washington, DC, United States
$70k–$90k; spot bonuses + annual performance-based...
Fully remote (u.s.-based)
Develop adversarial test suites
Craft multilingual prompts and jailbreaks
Analyze model outputs and report vulnerabilities
10a Labs is seeking an Ai Red Teamer to develop and run adversarial test suites for AI models, focusing on security and safety. The ideal candidate should have experience in red-teaming or related fields, proficiency in scripting, and strong communication skills in multiple languages

Job Summary

  • 10a Labs provides AI safety and threat intelligence for leading AI labs and technology platforms.
  • In this role, you will develop and run adversarial test suites for LLMs and image/video models, craft multilingual prompts, and analyze outputs to report vulnerabilities.
  • The company offers a competitive salary range of $70K–$90K, fully remote work (U.S.-based), comprehensive benefits, and opportunities for professional development and career growth.

Matching Summary

Match Score: 85

10a Labs is seeking an Ai Red Teamer to develop and run adversarial test suites for AI models, focusing on security and safety. The ideal candidate should have experience in red-teaming or related fields, proficiency in scripting, and strong communication skills in multiple languages.

Salary

$70K–$90K; Spot bonuses and annual performance-based bonus; Comprehensive health, dental, and vision, 401(k) plan

Skills & Requirements

Must-have

  • Develop adversarial test suites
  • Craft multilingual prompts and jailbreaks
  • Analyze model outputs and report vulnerabilities
  • Contribute to internal tooling development
  • Script basic tests in Python or Bash
  • Work with prompt-engineering tools

Nice-to-have

  • Full professional proficiency in Arabic, Chinese, Farsi, Portuguese, Russian, or Spanish
  • Prior work in content moderation or disinformation analysis
  • Experience with prompt-automation frameworks
  • Familiarity with vector search or LLM fine-tuning
  • Formal training in red-teaming or penetration testing

Key Requirements

  • 2-4 years of experience in red-teaming, security research, or trust & safety
  • Bachelor's degree or equivalent experience in CS, data science, linguistics, international studies, or security
  • Basic proficiency with Python and command-line tools
  • Demonstrated interest in AI safety or adversarial ML
  • Strong writing skills for vulnerability reports
  • Ability to rapidly context switch across domains and modalities

Work Rights

Not specified

Tailored Resume

Cover Letter