AI & Cloud Security
AI Security Engineer
Guardrails, prompt-injection defense, model governance, and platform hardening for LLM apps.
About this learning path
Own the security posture of LLM-powered products. From input/output guardrails to tool-use safety and platform hardening, this path prepares you to protect AI apps in production.
Career outcomes
- AI Security Engineer
- LLM Platform Security Engineer
Prerequisites
- Working knowledge of Python
- Familiarity with at least one cloud provider
- Basic understanding of REST APIs and web app security
Learning path modules
- 1
Threat model LLM applications end-to-end
Guided + challenge labs Knowledge check
- 2
Design input/output guardrails and safe tool-use patterns
Guided + challenge labs Knowledge check
- 3
Defend against prompt injection, data exfiltration, and jailbreaks
Guided + challenge labs Knowledge check
- 4
Implement model, prompt, and dataset governance
Guided + challenge labs Knowledge check
Capstone project
Design, implement, document, and defend a full environment you can show employers.
Labs & projects
Stage 1
Guided
Step-by-step build instructions.
Stage 2
Assisted
Fewer steps, more decisions.
Stage 3
Challenge
Objectives only — you solve it.
Stage 4
Capstone
Full environment, documented.
What you walk away with
- Portfolio of guardrail systems and red-team exercises
- Reference architectures for secure RAG and agent systems
- Interview readiness for AI security engineer roles
Join the waitlist
AI Security Engineer is opening later. Drop your email to get notified when enrollment opens — waitlist members get first access and early-bird pricing.
Learn at your pace
Access content on your own schedule.
Hands-on practice
Build real environments, not click-throughs.
Portfolio evidence
Documented projects you can show employers.
Support community
Get help from peers and mentors.