Skip to main content
aijobsok.Practical AI learning for curious builders
TopicsInterview Questions
  • Overview
  • All AI topics
  • Generative AI Fundamentals
    • What is Generative AI?
    • Transformers Architecture
    • Tokens, Context Windows, and Temperature
    • Prompt Engineering Best Practices
    • Generative AI Use Cases and Limitations
    • Prompt Patterns for Coding with AI
    • Prompt Patterns for Data Analysis
    • Prompt Patterns for Writing and Editing
  • Retrieval-Augmented Generation (RAG)
    • Introduction to RAG Architecture
    • Vector Embeddings and Chunking
    • Choosing a Vector Database
    • Building a RAG Pipeline
    • Advanced RAG
  • AI Agents & Orchestration
    • Autonomous AI Agents Explained
    • LangChain vs. LlamaIndex
    • Building Tool-Calling Agents
    • Multi-Agent Systems
    • Agent Memory Management
  • Model Context Protocol (MCP)
    • Introduction to MCP
    • Setting Up an MCP Server
    • Connecting Local Tools via MCP
    • Security and Authentication in MCP
    • Building Custom MCP Clients
  • Fine-Tuning Models
    • Fine-Tuning vs. RAG
    • Supervised Fine-Tuning (SFT)
    • Parameter-Efficient Fine-Tuning (PEFT)
    • Preparing Datasets
    • Fine-Tuning Open Models
  • Local AI & Open-Source Models
    • Running LLMs Locally
    • Quantization Explained
    • LM Studio Integration
    • High-Throughput Serving
    • Evaluating Model Benchmarks
  • Multimodal AI
    • Vision-Language Models (VLMs)
    • Diffusion Models Architecture
    • Audio Processing Pipelines
    • Multimodal RAG
    • Building Multimodal Chatbots
  • LLMOps (MLOps for LLMs)
    • Introduction to LLMOps
    • Prompt Tracking and Versioning
    • Evaluating LLM Outputs
    • API Cost and Latency Management
    • Deploying to Production
  • AI Security & Guardrails
    • Prompt Injection Risks
    • Implementing NeMo Guardrails
    • PII Redaction
    • Toxicity and Hallucination Filtering
    • Compliance for AI Applications
  • Python for AI Development
    • AI Environment Setup
    • API Integrations
    • Structured Outputs
    • Data Processing for AI
    • Rapid UI Prototyping
  • Classical Machine Learning
    • Supervised Learning Explained
    • Classification vs. Regression
    • Model Evaluation Metrics Explained
    • Overfitting, Underfitting, and Regularization
    • Feature Engineering Basics
  • Neural Networks & Deep Learning
    • How Neural Networks Work
    • Activation Functions Explained
    • Training with Backpropagation
    • CNNs vs. RNNs vs. Transformers
    • Avoiding Common Neural Network Training Pitfalls
  • AI Careers & Job Prep
    • AI Engineer vs. Data Scientist vs. ML Engineer
    • How to Break Into an AI Career
    • Building an AI Portfolio That Gets Interviews
    • AI Interview Prep Beyond Coding Puzzles
    • Understanding AI Salaries and the Job Market
  • AI Tools & Comparisons
    • ChatGPT vs. Claude vs. Gemini: How to Choose
    • Best AI Coding Assistants: What to Actually Compare
    • Cursor vs. GitHub Copilot: A Practical Comparison
    • A Framework for Choosing Any AI Tool
  • AI Coding Agents
    • What Are AI Coding Agents?
    • Claude Code, Cursor Agent, and Codex-Style CLIs Compared
    • Prompting and Steering a Coding Agent
    • Safety, Review, and Guardrails for Coding Agents
  • Context Engineering
    • What Is Context Engineering?
    • Managing Long Conversations and Context Windows
    • Getting Retrieval and Tool Results Into Context Well
    • Context Engineering for Multi-Step Agents
  • AI Evals & LLM-as-Judge
    • Why AI Products Need Evals
    • Designing Metrics: Exact Checks, Rubrics, and Reference Answers
    • Using an LLM as a Judge
    • Wiring Evals Into Development and Deployment
  • Video Generation & World Models
    • How AI Video Generation Models Work
    • Practical Use Cases for AI Video Generation Today
    • Evaluating and Reviewing Generated Video
  • Small Language Models & On-Device AI
    • What Are Small Language Models, and Why They Matter
    • Choosing Between a Small Model and a Large Hosted Model
    • Deploying Small Models to Edge and Mobile Devices
  • AI Regulation & Compliance
    • The AI Regulation Landscape: What Builders Need to Know
    • Understanding High-Risk AI Classification
    • Building AI Products With Compliance in Mind
Responsible learning

AI Content Disclaimer

AI systems and their surrounding tools change quickly. Use this site as a learning resource, not as a substitute for verification or professional judgment.

Verify important information

Technical examples, provider behavior, model capabilities, prices, policies, and security practices can change. Test examples in your own environment and consult current primary documentation before relying on them.

AI output can be wrong

Generative models can produce plausible but inaccurate, incomplete, biased, or unsafe output. Treat model responses as drafts or hypotheses. Check important claims, citations, calculations, code, and recommendations with appropriate human review.

Do not submit confidential information

Do not paste passwords, private keys, personal data, confidential business information, or regulated records into third-party tools merely because an example mentions them. Apply your own organization’s security, privacy, and retention requirements.

No professional advice

Nothing on this site is legal, medical, financial, employment, or professional security advice. Seek qualified advice for high-impact decisions.

Quick read

What should I learn first?

Begin with AI concepts, then move into how models learn from data.

Read the introduction →
aijobsok.

Learn the ideas shaping tomorrow.

TopicsInterview QuestionsGlossaryAboutContactPrivacyCookiesTermsAI Disclaimer
© 2026 aijobsok. Built for curious minds.