Description

You will lead AI red teaming initiatives, advancing adversarial cybersecurity research and enabling threat-driven risk management.

This role is on-site.

Responsibilities

• Plan and scope adversarial assessments for Generative AI systems.
• Execute scenario-based security testing to evaluate robustness, safety, and alignment.
• Assess GenAI risks including data poisoning, model extraction, and prompt injection.
• Collaborate with senior leadership to drive intelligence analysis and controls evaluation.
• Implement security controls for GenAI platforms and APIs.

Required Skills

• 5+ years of experience in information security or adversarial research.
• Advanced knowledge of Generative AI architectures and Large Language Models (LLMs).
• Hands-on experience with prompt engineering and adversarial planning.
• Deep understanding of OWASP Top 10 LLM 2025, MITRE ATLAS, and NIST AI RMF frameworks.
• Proficiency with Jira, ServiceNow, and Confluence for tracking and documentation.
• Strong skills in Power BI and Microsoft Suite (Visio, Project) for reporting and visualization.
• Ability to evaluate agentic risks and GenAI-related security threats.

Preferred Skills

• Familiarity with current regulations and ethical considerations for Generative AI.
• Experience with IBM Open Pages for risk management.

Key Skills

Education

Any Graduate