Description

You will assess and secure Generative AI architectures, including large language models, against adversarial threats and operational risks.

This role is on-site.

Responsibilities

• Plan and scope adversarial assessments for GenAI systems, focusing on prompt injection, data poisoning, and model extraction.
• Implement security controls for GenAI platforms and APIs, ensuring alignment with safety and robustness frameworks.
• Evaluate GenAI risks using OWASP Top 10 LLM 2025, MITRE ATLAS, and NIST AI RMF standards.
• Manage security testing scenarios and document regulatory, ethical, and safety considerations.
• Maintain project tracking and documentation using Jira, ServiceNow, and Confluence.

Required Skills

• 5+ years of experience in cybersecurity, with a focus on AI/ML security.
• Deep knowledge of Generative AI architectures, LLMs, and prompt engineering.
• Hands-on experience with adversarial assessment planning and scenario-based security testing.
• Familiarity with OWASP Top 10 LLM 2025, MITRE ATLAS, and NIST AI RMF.
• Proficiency with Jira, ServiceNow, IBM Open Pages, and Confluence.
• Experience with Power BI and the Microsoft Suite (Visio, Project, Word, Excel, PowerPoint).
• Bachelor's degree in a relevant technical field.

Key Skills

Education

Bachelor's degree