Agentic AI Security specialist

10-14years exp

Job Description: Agentic AI Security Engineer / AI Security Specialist
Role Overview
We are seeking a highly skilled Agentic AI Security Engineer to secure next-generation AI systems, including Large Language Models (LLMs), AI Agents, multi-agent ecosystems, and autonomous decision-making platforms. The ideal candidate will possess expertise in AI security engineering, LLM security, AI red teaming, governance frameworks, and security data science to help build, assess, and protect enterprise AI solutions.
This role will be responsible for identifying AI-specific attack vectors, implementing security controls and guardrails, conducting adversarial testing, and establishing governance practices across the AI lifecycle.
________________________________________
Key Responsibilities
Agentic AI Security Engineering
•    Design and implement security architectures for Agentic AI and autonomous AI systems.
•    Assess security risks associated with AI agents, multi-agent orchestration, tool usage, and autonomous decision-making workflows.
•    Define and implement security controls for AI agents interacting with enterprise applications, APIs, and external systems.
•    Conduct AI threat modeling and attack path analysis for agent-based architectures.
LLM & Model Security
•    Secure Large Language Models (LLMs), Foundation Models, and Generative AI solutions.
•    Evaluate model vulnerabilities, adversarial attack surfaces, and prompt-based exploitation techniques.
•    Implement controls against: 
o    Prompt Injection
o    Jailbreak Attacks
o    Data Leakage
o    Model Poisoning
o    Model Extraction
o    Model Theft
o    Adversarial Manipulation
o    Hallucination Risks
•    Assess security of Retrieval Augmented Generation (RAG) and AI Agent frameworks.
AI Red Teaming
•    Conduct offensive security assessments against AI/ML and GenAI systems.
•    Design adversarial attack scenarios targeting models, prompts, agents, and AI workflows.
•    Perform AI penetration testing and control validation exercises.
•    Leverage frameworks such as: 
o    MITRE ATLAS
o    MITRE ATT&CK
o    OWASP Top 10 for LLM Applications
AI Governance & Guardrails
•    Develop and implement AI governance frameworks and security policies.
•    Establish responsible AI controls and risk management practices.
•    Define and manage: 
o    Prompt Guardrails
o    Content Moderation
o    Data Protection Controls
o    Human-in-the-Loop Approvals
o    Model Access Controls
o    AI Risk Monitoring
•    Support compliance with enterprise AI governance standards and regulatory requirements.
Security Data Science
•    Apply data science and machine learning techniques to solve cybersecurity challenges.
•    Analyze AI-related security telemetry and threat intelligence datasets.
•    Develop predictive models and anomaly detection capabilities.
•    Evaluate model robustness, explainability, fairness, and resilience.
•    Collaborate with SOC, Threat Intelligence, and Security Engineering teams to strengthen AI-driven security capabilities.