AI Red Team Prompt Injection Analyst

About the role

Responsibilities

• Design and execute prompt injection attack campaigns against client LLM applications
• Craft novel injection payloads tailored to specific application architectures
• Test across multiple threat models: data exfiltration, privilege escalation, content manipulation
• Write actionable remediation reports with severity ratings and fix recommendations
• Develop reusable attack frameworks and testing methodologies
• Stay current with emerging injection techniques and defensive countermeasures

Requirements

• 5+ years in security research or penetration testing with LLM focus
• Deep understanding of prompt injection, jailbreaking, and LLM security
• Experience with LangChain, OpenAI API, and diverse LLM architectures
• Strong technical writing for client-facing security reports
• Ability to think adversarially and systematically about attack surfaces

Benefits

• Fully remote contract position
• Premium security consulting rate
• Exposure to diverse LLM applications and architectures
• Published case studies with client permission
• Potential conversion to permanent security lead

Keep exploring related roles

Use these topic pages to discover more roles in the same hiring cluster.