Zulia Shavaeva← Back to Zulia
Free AI and security guide/Learn

Learn

Thirteen skills that AI security postings ask for, ordered by how many of the 48 postings name them. Each has free resources by level, and where researched, a sourced brief with concepts, exercises and practice questions.

Optional paid courses and certifications

LLM security: prompt injection, jailbreaks, output handling

Understanding how attackers manipulate LLM inputs and outputs, and how to design applications that resist prompt injection, jailbreaks, and unsafe output handling.

44 of 48 postings. 21 resources, brief, 3 exercises.
Deep indexBrief

Python and coding for AI security work

Enough Python to build a small LLM or agent app, call model APIs, write tests against them and automate attacks or checks; 67 percent of the 48 postings ask for it.

32 of 48 postings. 24 resources, brief, 3 exercises.
Deep indexBrief

Agent and agentic system security: tool use, permissions, memory, multi-agent

Securing AI systems that plan, call tools, hold memory, and act semi-autonomously, often through multiple cooperating agents.

31 of 48 postings. 29 resources, brief, 3 exercises.
Deep indexBrief

Securing model and agent workloads on cloud platforms

Applying cloud security controls, identity boundaries and monitoring to model and agent workloads on AWS, Azure and GCP.

28 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief

AI red teaming and adversarial testing

Probing AI systems, especially LLMs, for exploitable weaknesses using adversary tactics and structured attack testing.

23 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief

AI system threat modelling and secure architecture

Mapping how an AI or agentic system can be attacked and designing the architecture and controls to reduce that risk.

22 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief

Application security for LLM-backed software

Applying secure design, review and testing practices to applications that embed LLMs, agents or RAG pipelines.

14 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief

AI governance, risk and compliance: NIST AI RMF, ISO/IEC 42001, EU AI Act, CSA AICM

Applying formal risk management, management-system, and regulatory frameworks to how an organisation builds, buys, and operates AI.

14 of 48 postings. 24 resources, brief, 3 exercises.
Deep indexBrief

RAG pipeline security: retrieval, vector stores, data poisoning

Securing the retrieval side of an LLM application, including the vector database, the documents fed into it, and the ways an attacker can poison or manipulate what gets retrieved.

12 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief

Model Context Protocol security: servers, tool poisoning, auth

Securing the client-server protocol that lets AI agents discover and call external tools, including malicious or compromised tool servers.

11 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief

Advisory and customer-facing delivery skills

Explaining AI risk and controls to clients and leadership, and delivering advisory work they can act on.

7 of 48 postings. 23 resources, brief, 3 exercises.
Deep indexBrief

Identity and least privilege for agents and tools

Scoping identities, tokens and permissions so agents and the tools they call can only do what they need to.

7 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief

Detection, logging and response for AI systems

Knowing what an attack on an LLM or agent looks like in logs, which signals to collect, and how to respond when a model or agent misbehaves.

4 of 48 postings. 25 resources, brief, 3 exercises.
Deep indexBrief