SOAR Automation Manager

The Operational Security Automation role evolves in 2024 to integrate generative AI and agentic AI as core drivers of security center operations. This position transforms traditional SOCs or VOCs into autonomous operational centers capable of contextual reasoning, decision-making, and action.

Key Responsibilities:

1. Intelligent AI Workflow Development
Design of self-adaptive playbooks using LLMs (GPT-4, Claude, Mistral)
Creation of orchestrated APIs for autonomous agentic workflows
Integration of MCP (Model Context Protocol) and Agent2Agent protocols
Development of AI agents for contextual automatic incident triage

2. AI Autonomous Operations Governance
Supervision of autonomous decisions with human validation mechanisms
ROI measurement of deployed generative AI systems
Compliance with AI Act, DORA, and NIS2 frameworks for autonomous AI
Performance management according to agentic SLAs/SLOs

3. AI Strategy and Innovation
Development of strategic roadmap for agentic AI implementation
Technology watch on generative model evolution
Integration of innovative perspectives from AI threat landscape
Benchmarking of SOAR platforms with agentic capabilities

4. AI Performance Management
Definition of specific KPIs for generative systems
Analysis of contextual relevance of autonomous decisions
Measurement of automatically generated playbook effectiveness
Continuous model optimization through fine-tuning

5. AI Skills Development
Planning of required competencies for the agentic AI era
Continuous training on fine-tuning and LLM optimization
Management of specialized technical resources in generative AI
Creation of AI upskilling programs

Required Experience:

10-12+ years in information Security with cloud and AI focus
5+ years of experience in managing a team of SOAR or SIEM members.
Mastery of agile methodologies adapted to AI cycles

Experience in Agentic SOAR Platforms
Tines AI with generative capabilities
XSOAR with Cortex XSIAM and integrated AI
IBM Resilient with advanced Watson AI
Swimlane with agentic modules

AI Protocols and Standards
Model Context Protocol (MCP) - Anthropic
Agent2Agent (A2A) - Google

AI PERFORMANCE INDICATORS:

Generative Metrics
Automatic playbook generation rate
Generated decision quality (precision/recall)
Response time reduction through AI
Measurable ROI of AI investments

Agentic Metrics
Validated autonomous decision rate
Containment latency with AI agents
Incidents resolved without human intervention
Performance of self-adaptive systems

Operational Metrics
SLA/SLO compliance with AI systems
Automatic threat pattern coverage
Scalability of deployed agentic solutions
Team adoption rates of AI tools

AI REGULATORY CONTEXT

Required Compliance
EU AI Act regulation
DORA directives for digital finance
NIS2 for network security

AI Risk Governance
Mapping of specific agentic AI risks
Procedures for validating autonomous decisions
AI audit and traceability mechanisms
Continuity plans for AI failures