Description

You will strengthen AI red teaming initiatives and advance adversarial cybersecurity research to enable threat-driven risk management.

This role is on-site.

Responsibilities

• Plan and scope adversarial assessments for Generative AI systems, including prompt engineering and scenario-based security testing.
• Evaluate GenAI risks such as data poisoning, model extraction, and prompt injection threats using frameworks like OWASP Top 10 LLM 2025 and MITRE ATLAS.
• Apply systems thinking and game theory to assess robustness, safety, and alignment in AI architectures.
• Collaborate with senior leadership to translate technical findings into professional risk assessments and controls evaluations.
• Implement security controls for GenAI platforms and APIs while ensuring compliance with current regulations and ethical standards.

Required Skills

• 10+ years of experience in cybersecurity, with advanced knowledge of Generative AI architectures and Large Language Models (LLMs).
• Hands-on experience with prompt engineering and adversarial assessment planning.
• Proficiency in Jira, ServiceNow, Confluence, and Power BI.
• Familiarity with Microsoft Suite tools including Visio and Project.
• Strong understanding of risk assessment, intelligence analysis, and professional communication.
• Experience utilizing GenAI platforms (ChatGPT, Gemini, or Claude) and implementing associated security controls.

Preferred Skills

• Familiarity with NIST AI RMF and frameworks for evaluating agentic risks.
• Experience with IBM Open Pages for risk management documentation.

Key Skills

Education

Any Graduate