LLM Security Evaluator & Adversarial Prompt Specialist

A leading cybersecurity firm in the United States is seeking a Large Language Models (LLM) Security Evaluation Expert to test and secure AI systems against potential vulnerabilities. The role involves designing adversarial prompts, assessing model integrity, and ensuring responsible AI operation. The ideal candidate will possess strong knowledge of LLMs, proven experience in prompt crafting, and a solid understanding of cybersecurity principles. Certification in offensive security is highly desirable.