Role & responsibilities

- Lead AI and agentic AI risk assessments, from initial gap analysis through readiness reviews and closing identified gaps, using recognized frameworks such as the NIST AI Risk Management Framework and OWASP Agentic AI guidance.

- Design and implement AI guardrails covering prompt injection defense, data leakage prevention, and unsafe tool use, referencing the OWASP Top 10 for Large Language Model Applications and MITRE ATLAS.

- Define agent identity, authorization, and lifecycle controls, distinguishing human initiated actions from agent initiated actions.

- Build and deploy agentic AI automations across operational, financial, and administrative workflows, with sandboxing to contain failures.

- Present findings, risk assessments, and automation recommendations to stakeholders,



translating technical detail into business decisions.

- Bring hands-on experience with AI or machine learning security, gained through prior consulting, engineering, or applied security roles.

Preferred candidate profile

- Above average completion of a technical degree (computer science, information security, or related field).

- Prior knowledge and certifications in cybersecurity, with working familiarity with NIST AI RMF, OWASP LLM and Agentic AI guidance, or MITRE ATLAS.

- Proven experience running stakeholder facing consulting engagements, comfortable owning a relationship end to end, not only technical delivery.

📌 AI Cybersecurity Specialist (Delhi)
🏢 Kairosvector
📍 Delhi