Remote LLM Security Engineer: Jailbreak & Prompt-Injection

Executive Staff Recruiters / ESR Healthcare; United States; Remote; USD 96,000 - 207,000; Full time

Job summary

Executive Staff Recruiters / ESR Healthcare is seeking an AI Jailbreak & Prompt-Injection Security Expert for a remote contractor role. You will design advanced methodologies to test AI safety, develop cross-domain elicitation strategies, and build robust evaluation frameworks against real-world adversarial threats.

Ideal candidates have extensive experience in adversarial ML, LLM red teaming, and AI safety evaluation, with a strong publication or open-source background.

Qualifications

• 5+ years of expertise in adversarial ML, LLM red teaming, AI safety evaluation, or related security domain.
• Strong research and testing background in ethical jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
• PhD or MS in CS, cybersecurity, ML, or equivalent professional background.

Responsibilities

• Design and implement methods to evaluate AI safety, jailbreaks, red teaming, and prompt-injection risks.
• Create cross-domain elicitation strategies to uncover multi-turn adversarial patterns in AI models.
• Develop and maintain regression test suites for jailbreak and prompt-injection vulnerabilities.
• Build evaluation frameworks to stress-test AI models against real-world threats and improve robustness.
• Translate security findings into actionable improvements for model safety and risk mitigation.
• Document methodologies and findings in clear, structured reports for technical and non-technical audiences.

Skills

Adversarial ML

LLM red teaming

AI safety eval

Security research

Technical writing

Cross-functional collab

Education

Advanced degree in CS/cybersecurity/ML

Job description

Executive Staff Recruiters / ESR Healthcare is seeking an AI Jailbreak & Prompt-Injection Security Expert for a remote contractor role. You will design advanced methodologies to test AI safety, develop cross-domain elicitation strategies, and build robust evaluation frameworks against real-world adversarial threats.

Ideal candidates have extensive experience in adversarial ML, LLM red teaming, and AI safety evaluation, with a strong publication or open-source background.