Lead AI Safety & Adversarial Testing Engineer

Expert Talent Pool

United States

Remote

USD 140,000 - 190,000

Full time

3 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Expert Talent Pool in the United States is seeking an experienced security testing professional to design and lead red team campaigns, develop jailbreak techniques, and test AI agents for prompt injection.

You will evaluate tool-use capabilities, design bias testing frameworks, and conduct safety audits against policies, documenting gaps and recommending fixes. Strong written English and five+ years of experience are required; familiarity with OWASP LLM Top 10 is a plus.

Qualifications

  • Hands-on AI safety testing experience.
  • Experience designing test plans, threat models or audits.
  • Strong written English.

Responsibilities

  • Design and lead red teaming campaigns to identify attack vectors in high-risk model capabilities.
  • Develop and document jailbreak techniques for reproducibility.
  • Test agents for prompt injection when processing untrusted inputs.
  • Probe tool-use capabilities such as code execution, browsing and messaging for misuse.
  • Design bias testing frameworks and assess fairness across demographic groups and languages.
  • Conduct safety audits against written policies and document compliance gaps.
  • Write content moderation guidelines, review edge cases and assess moderators' work.
  • Rate finding severity and recommend fixes.

Skills

Security testing
Trust & safety
Policy understanding
Adversarial ML
Threat modeling

Tools

Burp Suite
Garak
PyRIT
OWASP LLM Top 10

Job description

Expert Talent Pool in the United States is seeking an experienced security testing professional to design and lead red team campaigns, develop jailbreak techniques, and test AI agents for prompt injection.

You will evaluate tool-use capabilities, design bias testing frameworks, and conduct safety audits against policies, documenting gaps and recommending fixes. Strong written English and five+ years of experience are required; familiarity with OWASP LLM Top 10 is a plus.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

AI Safety Testing Lead — Red Team & Jailbreak Expert
AI Safety Testing Lead — Red Team & Jailbreak Expert

OpenAI, Inc. • United States

Remote
USD 120,000 - 180,000
AI Safety Testing Lead (Fully Remote)
AI Safety Testing Lead (Fully Remote)

OpenAI, Inc. • United States

Remote
USD 120,000 - 180,000
AI Jailbreak & Prompt-Injection Security Expert - Remote
AI Jailbreak & Prompt-Injection Security Expert - Remote

YO AI Labs • United States

Remote
USD 83,000 - 165,000
AI Safety & Red Teaming Specialist
AI Safety & Red Teaming Specialist

Weekday AI • United States

Remote
USD 69,000 - 124,000
Expert Talent Pool, Safety Testing (Expert, 5+ Years)
Expert Talent Pool, Safety Testing (Expert, 5+ Years)

Expert Talent Pool • United States

Remote
USD 140,000 - 190,000
Remote AI Safety & Red Teaming Architect
Remote AI Safety & Red Teaming Architect

Weekday • United States

Remote
USD 69,000 - 124,000
Expert Talent Pool, Safety Testing (Expert, 5+ Years)
Expert Talent Pool, Safety Testing (Expert, 5+ Years)

Clera • United States

Remote
USD 103,000 - 241,000
Competitive hourly rate
AI Jailbreak & Prompt-Injection Security Expert
AI Jailbreak & Prompt-Injection Security Expert

Remotebridge • United States

Remote
USD 110,000 - 165,000
Remote AI Security Engineer: Jailbreak & Prompt-Injection Expert
Remote AI Security Engineer: Jailbreak & Prompt-Injection Expert

YO AI Labs • United States

Remote
USD 83,000 - 165,000
AI Red Team Pro: LLM Safety & Adversarial Testing
AI Red Team Pro: LLM Safety & Adversarial Testing

handshake • United States

Remote
USD 83,000 - 165,000