LLM Security Evaluation Expert

Job Summary

A company is looking for a Large Language Models (LLM) Security Evaluation Expert to rigorously test the security and integrity of LLMs.

Key Responsibilities:

• Develop and implement adversarial prompts targeting LLM vulnerabilities
• Systematically test LLMs against designed adversarial prompts and analyze responses for security weaknesses
• Assess the model's resistance to exploitation and ensure secure behavior

Required Qualifications:

• Strong knowledge of LLM architecture, training processes, capabilities, and limitations
• Experience in crafting prompts to elicit specific behaviors or bypass restrictions in LLMs
• Understanding of cybersecurity principles and common attack vectors in AI/ML systems
• Offensive Security Certified Professional (OSCP) or Certified Ethical Hacker (CEH)
• Ability to analyze complex systems and identify vulnerabilities systematically