Use Code TRYNOW15 for a One-Time, Extra 15% OFF at KodeKloud

AWS AI Learning Path

I Know
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Master AI, ML & Context Foundations
Learn by Doing - Prompt Engineering 101
5h 0m
Start Course
Detailing for Clarity
Persona Play
Delimiters
Step-by-Step Clarification
Illustrating Through Examples
Specifying Output Length
More details
Hide details
Vector Databases
4h 26m
Start Course
Vector Database Foundations
From Data to Vectors: The Embedding Layer
Vector Similarity Explained
Building Vector Storage on AWS S3
Vector Database Landscape
Vector Database Internals
More details
Hide details
MCP For Beginners
2h 31m
Start Course
mcp Introduction
Core Concepts
Leveraging MCP for Daily Work
More details
Hide details
AI Agents Fundamentals
1h 33m
Start Course
LLMs work in real time
Embeddings & Vector Representations
LangChain
Vector Databases Deep Dive
Build Semantic Search Engine
Model Context Protocol
Advanced MCP Concepts
More details
Hide details
Build with Generative AI & Developer Tools
Introduction to OpenAI
4h 10m
Start Course
Text generator
Advanced usage techniques
Content moderation
Image generation and captioning
Fine-tuning techniques
More details
Hide details
Claude Code For Beginners
8h 32m
Start Course
Getting Started with Claude Code
Working with Claude Code
Code Review with Claude Code
Security Auditing with Claude Code
Terminal Productivity
Advanced Features
More details
Hide details
Optional
Cursor AI
3h 48m
Start Course
Introduction to Cursor
Mastering Autocompletion in Cursor
Interacting with your Codebase
Inline Editing and Debugging in Cursor
Terminal Productivity
Customizing Cursor
More details
Hide details
Optional
Generative AI in Practice: Advanced Insights & Operations
3h 52m
Start Course
Evolution of AI Models
Retrieval-Augmented Generation (RAG)
AI Application(LLM) on Azure
Large Language Models(LLM)
Prompting Techniques in LLM
Application and Assessment of LLMs
More details
Hide details
Running Local LLMs With Ollama
2h 15m
Start Course
Running Your First Model
Essential Ollama CLI Commands
Ollama REST API Endpoints 
OpenAI Compatibility for Ollama
Customizing Models
Uploading Custom Models
More details
Hide details
Explore AWS AI & GenAI Fundamentals
AWS Certified AI Practitioner
8h 5m
Start Course
Fundamentals of AI and ML
Fundamentals of Generative AI
Applications of Foundation Models
Security, Compliance, and Governance for AI Solutions
Guidelines for Responsible AI
More details
Hide details
Fundamentals of MLOps
5h 8m
Start Course
Data Collection and Preparation
Model Development and Training
Model Deployment and Serving
Automating Insurance Claim Reviews with MLflow and BentoML
Data Security and Governance
AWS SageMaker
More details
Hide details
Loop Engineering
0h 45m
Start Course
introduction
The Scorekeeper
Six Components of Loop Engineering
Automations
Worktrees
Connectors & Plugins
Sub-agents
Memory
More details
Hide details
Optional
Build with AWS Machine Learning & SageMaker
AWS Machine Learning Associates
9h 12m
Start Course
Data Preparation for Machine Learning
ML Model Development
Deployment and Orchestration of ML Workflows
ML Solution Monitoring, Maintenance, and Security
More details
Hide details
AWS SageMaker
23h 55m
Start Course
SageMaker Introduction
SageMaker User Interface
Persona SageMaker Activities - Data Engineer
Persona SageMaker Activities - Data Scientist
Persona SageMaker Activities - MLOps Engineer
More details
Hide details
Scale Enterprise AWS GenAI & MLOps
AIOps - Learn By Doing

How long will it take for me to complete?

I can spend
hours / day
2
4
6
≈ 10 Weeks
≈ 7 Weeks
≈ 4 Weeks
≈ 2-3 Months
≈ 5 Weeks
≈ 4 Weeks
≈ 3 Weeks
≈ 2 Months
≈ 4 Weeks
≈ 3 Weeks
≈ 2 Weeks
≈ 1-2 Months
* This is based on averages from our students. This may change depending on your experience and level of expertise.

Success!!

Clear the KCNA exam with flying colors
Start the Test

Test your Readiness for Free!

The skills test is a hands-on exam that helps you identify where you stand today in your preparation for your DevOps exam. Do you know about Git enough to attempt the exam? Find out now!

AI learning paths

Path

General AI & AI Engineering

10 Courses
106h
Path

Azure AI

10 Courses
139h
Path

Kubernetes & Cloud Native AI

13 Courses
120h
Path

AWS AI

12 Courses
127h

Role based learning paths

Path

System
Administrator

13 Courses
341h
Path

Kubernetes
Administrator

12 Courses
250h
Path

DevOps
Engineer

17 Courses
350h
Path

Site Reliability
Engineer

13 Courses
320h
View All

FAQs

What is CI/CD?

CI/CD stands for Continuous Integration and Continuous Deployment. It is a set of practices and tools that enable developers to automatically build, test, and deploy software applications in a consistent and streamlined manner.

What is the difference between Continuous Integration and Continuous Deployment?

Continuous Integration (CI) focuses on automating the process of merging code changes from multiple developers into a shared repository and running automated tests to detect integration issues. Continuous Deployment (CD) takes CI a step further by automating the deployment of successfully tested code changes to production environments.

What are the benefits of implementing CI/CD?

CI/CD brings several benefits, including increased development speed, faster time to market, improved code quality, early bug detection, reduced manual errors, and easier collaboration among development teams.

What are some popular CI/CD tools?

Some popular CI/CD tools include Jenkins, GitLab CI/CD, CircleCI, Travis CI, TeamCity, and GitHub Actions. These tools provide automation capabilities for building, testing, and deploying applications.

How does CI/CD integrate with version control systems?

CI/CD tools integrate with version control systems, such as Git, to automatically trigger build and deployment processes whenever changes are pushed to the repository. This ensures that code changes are continuously tested and deployed.

What is the role of automated testing in CI/CD?

Automated testing is a crucial component of CI/CD. It includes unit tests, integration tests, and other types of automated tests that are executed as part of the CI/CD pipeline. These tests ensure the quality and reliability of the software before it is deployed.

Can CI/CD be used with containerized applications?

Yes, CI/CD is well-suited for containerized applications. Containers provide a consistent and reproducible environment for building, testing, and deploying applications, making it easier to integrate CI/CD pipelines into container-based workflows.

What are some common challenges in implementing CI/CD?

Some common challenges include managing complex deployment pipelines, ensuring compatibility across different environments, handling database migrations, maintaining good test coverage, and managing secrets and configurations securely.

Is CI/CD applicable only to cloud-based applications?

No, CI/CD can be applied to applications deployed in various environments, including on-premises, hybrid cloud, and multi-cloud environments. The principles of CI/CD can be adapted to different deployment scenarios.

What skills are important for implementing CI/CD?

Skills in version control systems (e.g., Git), scripting and automation (e.g., Bash, Python), knowledge of CI/CD tools, containerization (e.g., Docker), and infrastructure-as-code (e.g., Terraform) are valuable for successful implementation of CI/CD.

FAQs

Why choose the AWS AI pat

AWS is the largest cloud provider, and Amazon SageMaker is a cornerstone of enterprise ML. This path gives you technicalexpertise in building, training, tuning and deploying both traditional ML and generative models on AWS — highly indemand, well-paid skills.

Where should I start my learning journey?

  • Complete the shared foundations (Steps 1 & 2) — ML basics, prompt engineering, agents, and building with OpenAI,Claude and local LLMs.
  • Then establish AWS literacy with the AWS Certified AI Practitioner before going deep on SageMaker.

Do I need AWS experience before starting?

No prior AWS experience is required. The AWS Certified AI Practitioner course builds your baseline understanding of AWScloud AI services from the ground up before you move into hands-on SageMaker work.

Which certifications does this path prepare me for?

  • AWS Certified AI Practitioner — foundational cloud-AI certification (Step 3).
  • AWS Certified Machine Learning Engineer – Associate — the professional goal, paired with a deep SageMaker course(Step 4).

What is the recommended progression?

  1. Master AI, ML & Context Foundations
    Prompt Engineering, Vector Databases, MCP, AI Agents
  2. Build with Generative AI & Developer Tools
    OpenAI, Claude Code, Cursor AI, Ollama
  3. Explore AWS AI & GenAI Fundamentals
    AWS AI Practitioner, MLOps / Loop Engineering
  4. Build with AWS ML & Sage
    MakerAWS ML Engineer – Associate, SageMaker Deep Dive

How long will it take to complete?

The full path is roughly 127 hours. Note the SageMaker deep dive alone is 24 hours of video — the single biggestmodule. From scratch: 2 hrs/day → ~10 weeks, 4 hrs/day → ~5 weeks, 6 hrs/day → ~4 weeks.