Must‑Have Qualifications (Hard Filters)
- Strong knowledge of AI security frameworks: EU AI Act, MITRE ATLAS, OWASP Top 10 for LLM/ML
- Hands‑on AI security experience: RAG, MCP, Agentic systems (design → production)
- Security architecture & engineering: Proven track record designing scalable, resilient solutions
- Offensive AI security: LLM penetration testing, red teaming, guardrail design/implementation
- Playbook creation: Security reviews, risk assessments, consistent evaluation frameworks
- Stakeholder influence: Ability to drive measurable improvements in AI security posture
- Compliance knowledge: NIST, ISO, GDPR, emerging AI regulations
- Technical communication: Clear documentation, reporting, and stakeholder facilitation
Responsibilities
- Architect and implement robust AI security frameworks and secure coding practices
- Conduct vulnerability assessments and penetration testing on AI models/systems
- Collaborate with data scientists/engineers to embed security in the AI lifecycle
- Track and apply emerging AI security standards (EU AI Act, NIST, ISO, GDPR)
- Lead AI security research, innovation, and POCs for new threat models
- Prepare SOPs, protocols, and security reports for audit readiness
- Provide advisory and mentorship on AI security principles and practices
- Guide adoption of governance principles and reference model architectures
Preferred Experience
- Offensive AI security (prompt injection, jailbreaks, adversarial ML)
- Experience with AI commerce/economy systems (monetization, creator platforms)
- Polyglot data modeling and semantic model design
- Familiarity with AI workload optimization for performance/cost/security
- Relevant certifications: CISSP, CEH, OSCP, SC‑300, or equivalent