🌍 AI Jailbreak & Prompt-Injection Security Expert, Remote- Contract
Core
Design and implement advanced methodologies for evaluating AI system safety, focusing on ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse scenarios.
Role type
Contract AI security researcher (LLM red teaming)
Builds
Evaluation frameworks and regression test suites for AI model safety
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models
Required skills
Ethical jailbreaks, LLM red teaming, Prompt injection, Tool-use abuse, Adversarial machine learning, Cross-domain elicitation, Regression testing, Evaluation framework design, Security findings translation, Technical documentation
Preferred skills
Adversarial AI attacks research, Published research in AI security, Open-source tools contribution, Conference presentations, Multi-disciplinary project experience, LLM architecture familiarity, Prompt engineering techniques, Security assessment tools
