Description

• Advanced knowledge of Generative AI architectures, including large language models (LLMs).
• Hands-on experience with prompt engineering and planning and scoping adversarial assessments.
• Comprehensive understanding of GenAI-related risks, such as data poisoning, model extraction, and prompt injection threats, and familiarity with OWASP Top 10 LLM 2025 and agentic risks.
• Familiarity with frameworks for evaluating robustness, safety, and alignment in GenAI systems such as OWASP, MITRE ATLAS, and NIST AI RMF.
• Proven ability to manage and plan GenAI assessments and scenario-based security testing.
• Awareness of current regulations, ethical, and safety considerations related to Generative AI.
• Experience utilizing GenAI platforms, APIs, and implementing associated security controls.

 
Required Tools

• Jira
• ServiceNow
• IBM Open Pages
• Confluence
• ChatGPT, Gemini, or Claude
• Power BI
• Microsoft Suite of Tools (Visio, Project, Word, Excel, PowerPoint)

Key Skills

Education

Bachelor's degree