Advertisements

Agentic AI Security & LLM Governance Career Bootcamp

Advertisements
Hands-on training in AI security, agentic systems, and LLM governance to become a Principal AI Security Engineer.
1
1/5
(26) Ratings
0 students
Created by Arjun Vaid
Advertisements

What you'll learn

  • Explain how AI security differs from traditional application security and identify risks unique to LLMs, RAG systems, tool-calling applications, and memory
  • Design secure agentic AI architectures using layered controls, trust boundaries, least privilege, human approvals, and policy enforcement.
  • Identify, execute, and defend against prompt injection, jailbreaks, document poisoning, memory poisoning, parameter injection, and unauthorized agent actions.
  • Build secure AI applications that include chat interfaces, RAG pipelines, tool calling, persistent memory, and autonomous agents.
  • Implement prompt validation, input sanitization, risk scoring, output filtering, context isolation, trusted-source validation, and AI guardrails.
  • Create an integrated AI Security Gateway that protects prompts, retrieved content, tools, memory, model responses, and agent workflows.
  • Establish enterprise AI governance using inventories, ownership models, lifecycle controls, risk assessments, approval gates, policies, and evidence management.
  • Build governance dashboards for AI usage, cost, risk, model evaluation, drift, prompt quality, sensitive-data exposure, incidents, and human oversight.
  • Map operational AI controls to frameworks and standards including NIST AI RMF, ISO/IEC 42001, and the EU AI Act.
  • Communicate AI security risks, control gaps, remediation priorities, and governance recommendations to executives, engineers, risk teams, auditors and others
This course includes:
26.5 total hours on-demand video
0 articles
30 downloadable resources
158 lessons
Full lifetime access
Access on mobile and TV
Certificate of completion
Advertisements

Course content

Requirements

  • No previous AI security or governance experience is required; the course begins with foundational concepts.
  • Basic familiarity with computers, software applications, and internet technologies will be helpful.
  • Beginner-level Python knowledge is recommended, but the practical exercises are explained step by step.
  • A computer capable of running Python, Visual Studio Code, and the course project files is required.
  • Students should be comfortable installing software and running commands in a terminal or command prompt.
  • Basic awareness of APIs, databases, cloud applications, or cybersecurity concepts is useful but not mandatory.
  • Docker is introduced for packaging the final secure AI application; prior Docker experience is not required.
  • An interest in AI security, generative AI, risk management, compliance, or enterprise governance is the most important prerequisite.

Description

This course contains the use of artificial intelligence.

Step into one of the fastest-growing career paths in technology with Agentic AI Security & LLM Governance Career Bootcamp, a comprehensive, hands-on program designed to help you secure, monitor, govern, and lead modern artificial intelligence systems.

As organizations adopt Generative AI, Large Language Models, Retrieval-Augmented Generation, and autonomous AI agents, traditional cybersecurity practices are no longer enough. AI applications introduce new risks, including prompt injection, jailbreak attacks, document poisoning, memory manipulation, unauthorized tool execution, sensitive data exposure, hallucinations, and uncontrolled agent behavior. This course gives you the practical skills required to understand these threats, attack vulnerable systems responsibly, implement effective defenses, and establish enterprise-grade governance controls.

You will begin with the core responsibilities of a Principal AI Security Engineer, including secure AI architecture, risk assessment, enterprise controls, technical leadership, and communication with executives, legal teams, auditors, and product leaders. You will then build your own AI chat assistant and progressively enhance it with RAG, tool calling, persistent memory, and autonomous agent capabilities.

Throughout the course, you will test real-world AI attack scenarios and implement practical defenses such as prompt validation, risk scoring, input filtering, output guardrails, context isolation, trusted-source validation, least-privilege tool permissions, human approval workflows, secure memory controls, and agent decision validation. You will also build a complete AI Security Gateway that integrates security across prompts, models, retrieved documents, tools, memory, and agent workflows.

The governance portion of the course takes you beyond security engineering into enterprise AI governance, responsible AI, AI risk management, and regulatory compliance. You will learn how to create an enterprise AI inventory, track usage and cost, evaluate model performance, monitor drift, govern prompts and responses, oversee agent actions, protect sensitive data, and manage governance evidence.

You will build dashboards and practical projects covering AI risk scoring, model evaluation, hallucination monitoring, prompt traceability, human oversight, RAG governance, policy management, compliance mapping, approval workflows, incident management, audit trails, and executive reporting. You will also learn how to align operational controls with major frameworks and standards, including the NIST AI Risk Management Framework, ISO/IEC 42001, and the EU AI Act.

By the end of the course, you will have created a portfolio of hands-on AI security and governance projects, including an AI security gateway, risk remediation engine, model evaluation dashboard, agent activity monitor, guardrail enforcement service, incident center, and an Enterprise AI Governance Command Center.

This bootcamp is ideal for cybersecurity professionals, AI engineers, developers, architects, governance specialists, auditors, consultants, risk leaders, and career changers preparing for roles such as AI Security Engineer, LLM Security Engineer, Principal AI Security Engineer, AI Governance Specialist, Responsible AI Lead, or AI Risk Manager.

Build the technical, governance, and leadership skills required to secure the next generation of intelligent systems.

Who this course is for:

  • Cybersecurity professionals who want to specialize in LLM security, agent security, and generative AI risk.
  • AI engineers, machine-learning engineers, and developers responsible for building secure AI applications.
  • Application security, cloud security, product security, and security architecture professionals expanding into AI security.
  • Governance, risk, compliance, privacy, audit, and responsible-AI professionals who need practical technical knowledge.
  • Enterprise architects and solution architects designing production AI, RAG, agentic, and tool-calling platforms.
  • Technology leaders, engineering managers, CISOs, AI governance leaders, and risk executives responsible for enterprise AI adoption.
  • Consultants and forward-deployed engineers helping organizations implement secure and governed AI solutions.
  • Students and career changers preparing for roles such as AI Security Engineer, Principal AI Security Engineer, AI Governance Specialist, AI Risk Manager, or Responsible AI Lead.
  • Professionals preparing to lead AI security assessments, governance programs, red-team exercises, control implementations, or regulatory readiness initiatives.
  • Anyone seeking a project-based portfolio that demonstrates practical skills across AI security engineering and enterprise LLM governance.
Advertisements
JULFREE01
Advertisements
Advertisements
Free Online Courses with Certificates
Logo
Register New Account