Description

Own the security design, threat modeling, and tooling for GenAI and multi-agent systems.

This role is hybrid.

Responsibilities

• Lead threat modeling and risk analysis for GenAI systems, identifying misuse patterns and security gaps.
• Implement and maintain AI security policies, including controls for prompt injection, topic safety, and output guardrails.
• Operate and tune AI security tools for anomaly detection, vulnerability identification, and behavioral monitoring.
• Apply Python to automate AI security checks, monitoring tasks, and governance workflows.
• Contribute to compliance with AI regulations (EU AI Act, NIST AI RMF, GDPR) through documentation and control validation.

Required Skills

• 3+ years in Cybersecurity with at least 2 years focused on technical GenAI security.
• Strong knowledge of cybersecurity principles, threat modeling, and risk assessment.
• Expertise in GenAI security, including adversarial attack mitigation and guardrail tuning.
• Proficiency in Python for GenAI development and security automation.
• Hands-on experience with AI security tools (garak, giskard, fuzzyai) and manual testing.
• Familiarity with AI security frameworks (NIST AI RMF, OWASP LLM Red Teaming Guide & Top 10).
• Experience with Streamlit, AutoGen, Semantic Kernel, or smolagents.

Preferred Skills

• Experience with multi-agent AI systems and agentic workflows.

Key Skills

Education

Any Graduate