Adversarial Machine Learning Specialist

Join a cutting-edge AI Red Team as an Adversarial Machine Learning Specialist, focusing on security challenges in LLM-driven systems. Optimize AI resilience through rigorous testing and vulnerability analysis.

This hands-on technical role is essential for enhancing enterprise-scale AI product security. Ideal candidates have robust experience in adversarial machine learning, including prompt injection and model jailbreak techniques. You will execute real-world simulations and collaborate with engineering teams to address identified vulnerabilities efficiently.

Key Responsibilities

• Conduct adversarial testing for AI and LLM systems
• Execute real-world attack simulations, including prompt injection
• Develop automation scripts for attack scenarios
• Analyze model behavior under pressure
• Document findings clearly and thoroughly

Requirements

• Strong experience in adversarial ML or AI security research
• Expertise with LLM-based systems like OpenAI
• Proficient in Python for custom tooling
• Familiarity with API-based model deployments
• Background in cybersecurity is a plus

Leverage your skills in adversarial thinking to secure next-generation AI systems before deployment.