COMPLETE SYLLABUS

MLOps, LLMOps, AIOps & AI Agents

A production-focused curriculum covering DevOps foundations, machine learning operations, large language models, AI agents, AIOps, security, governance, and real-world capstone projects.

Jump to Modules View on Medium

Table of Contents

Module 1: DevOps Foundations for MLOps Module 2: Data Engineering & ML Fundamentals Module 3: MLOps — Machine Learning Operations Module 4: Cloud MLOps with AWS Module 5: LLMOps — Large Language Model Operations Module 6: AI Agents and Autonomous Systems Module 7: AIOps — AI for IT Operations Module 8: Production AI Security, Governance & Reliability Module 9: Real-World Capstone Projects
Module 1: DevOps Foundations for MLOps
1.1 Linux and Shell Scripting
  • Linux Commands and File System Management
  • Bash Scripting and Automation
  • Process and Service Management
  • Networking and Troubleshooting
  • Environment Variables and Permissions
1.2 Python Programming for AI and ML
  • Python Basics and Data Types
  • Control Structures and Loops
  • Lists, Tuples, Dictionaries and Sets
  • Functions and Modules
  • Object-Oriented Programming
  • Exception Handling
  • File and OS Operations
  • JSON, YAML and Configuration Management
  • Virtual Environments and Package Management
  • Logging and Debugging
  • Concurrency and Parallelism
  • Networking and REST APIs
  • Testing with Pytest
  • NumPy and Pandas Fundamentals
  • Boto3 for AWS Automation
1.3 Git and Version Control
  • Git Fundamentals and Workflows
  • Branching and Merging Strategies
  • Pull Requests and Code Reviews
  • Git Hooks and Repository Management
  • Version Control Best Practices for ML Projects
1.4 Docker and Containerization LAB
  • Docker Architecture and Fundamentals
  • Dockerfile Best Practices
  • Images, Containers, Volumes and Networking
  • Multi-Stage Builds and Image Optimization
  • Docker Compose
  • Container Security and Scanning
  • Hands-on: Containerizing a Python ML Application
1.5 Kubernetes for AI Workloads LAB
  • Kubernetes Architecture and Components
  • Pods, Deployments and Services
  • ConfigMaps and Secrets
  • Persistent Volumes and Claims
  • Ingress and Network Policies
  • Resource Requests, Limits and Autoscaling
  • Helm Fundamentals
  • GPU Workload Fundamentals
  • Hands-on: Deploying an ML Inference Service on Kubernetes
1.6 Infrastructure as Code LAB
  • Terraform Fundamentals and Modules
  • State Management and Remote Backends
  • Ansible Configuration Management
  • AWS CloudFormation
  • Infrastructure Provisioning for ML Workloads
  • Hands-on: Automating ML Infrastructure on AWS
1.7 CI/CD for AI Applications LAB
  • Jenkins Pipelines
  • GitHub Actions
  • Build, Test and Release Automation
  • Artifact and Container Image Management
  • Security Scanning and Quality Gates
  • Deployment Strategies and Rollbacks
  • Hands-on: CI/CD Pipeline for an ML Application
1.8 Cloud Computing for AI
  • AWS, Azure and GCP Fundamentals
  • Cloud Networking and IAM
  • Compute, Storage and Managed Services
  • Managed ML Platforms
  • Cloud Architecture for AI Workloads
  • Cost Optimization and Resource Management
1.9 Monitoring and Observability LAB
  • Metrics, Logs and Distributed Tracing
  • Prometheus and Grafana
  • ELK/EFK Stack
  • OpenTelemetry Fundamentals
  • CloudWatch Monitoring and Alarms
  • Service-Level Indicators and Objectives
  • Hands-on: Monitoring a Containerized Application
Module 2: Data Engineering and Machine Learning Fundamentals
2.1 Data Engineering for AI LAB
  • SQL Fundamentals for ML
  • Data Ingestion and Transformation
  • ETL and ELT Pipelines
  • Batch and Streaming Processing
  • Data Lakes and Object Storage
  • Apache Spark Fundamentals
  • Data Validation and Schema Management
  • Data Lineage and Data Quality
  • Data Pipeline Testing and Recovery
  • Hands-on: Building a Data Preparation Pipeline
2.2 Mathematics, Statistics and Probability
  • Descriptive Statistics
  • Probability Distributions
  • Mean, Median, Variance and Standard Deviation
  • Conditional Probability and Bayes’ Theorem
  • Correlation and Covariance
  • Sampling and Hypothesis Testing
  • Vectors and Matrices Fundamentals
  • Gradient Descent Fundamentals
2.3 Machine Learning Fundamentals
  • AI vs ML vs Deep Learning
  • Supervised and Unsupervised Learning
  • Regression and Classification
  • Clustering and Dimensionality Reduction
  • Feature Engineering and Data Preprocessing
  • Exploratory Data Analysis
  • Training, Validation and Test Datasets
  • Cross-Validation and Hyperparameter Tuning
  • Overfitting, Underfitting and Data Leakage
  • Model Evaluation Metrics
  • Scikit-learn Pipelines
  • Model Serialization and Inference
2.4 Core Machine Learning Algorithms LAB
  • Linear Regression
  • Logistic Regression
  • Decision Trees
  • Random Forests
  • Gradient Boosting Fundamentals
  • K-Nearest Neighbors
  • Support Vector Machines
  • K-Means Clustering
  • Anomaly Detection Algorithms
  • Hands-on: Building and Evaluating ML Models
2.5 Deep Learning Fundamentals LAB
  • Neural Network Architecture
  • Activation and Loss Functions
  • Forward Propagation and Backpropagation
  • PyTorch Tensors and Autograd
  • Training and Evaluating Neural Networks
  • GPU, CUDA and Memory Fundamentals
  • Model Checkpoints and Inference
  • Transformer Architecture Fundamentals
  • Attention and Tokenization
  • Hands-on: Training a Basic Neural Network
Module 3: MLOps — Machine Learning Operations
3.1 MLOps Fundamentals
  • ML Lifecycle and MLOps Maturity Models
  • MLOps vs DevOps
  • ML System Architecture
  • Reproducibility and Experiment Management
  • ML Deployment Challenges
  • Production ML Best Practices
3.2 Data and Feature Management LAB
  • Dataset Versioning with DVC
  • Data Validation and Data Contracts
  • Feature Engineering Pipelines
  • Feature Stores with Feast
  • Offline and Online Features
  • Data Drift and Data Quality Monitoring
  • Hands-on: Versioning Datasets and Building Feature Pipelines
3.3 Experiment Tracking LAB
  • MLflow Tracking
  • Weights & Biases
  • Experiment Comparison
  • Hyperparameter Optimization
  • Reproducible Training
  • Model Artifact Management
  • Hands-on: Building an Experiment Tracking Workflow
3.4 Model Registry and Governance LAB
  • Model Registry Fundamentals
  • Model Versioning and Lineage
  • Model Approval and Promotion
  • Model Metadata and Artifact Storage
  • Model Reproducibility
  • Model Rollback and Lifecycle Management
  • Hands-on: Building a Model Registry Workflow
3.5 ML Pipeline Orchestration LAB
  • Apache Airflow
  • Kubeflow Pipelines
  • AWS SageMaker Pipelines
  • Azure ML Pipelines
  • Vertex AI Pipelines
  • Workflow Scheduling and Dependency Management
  • Pipeline Retries and Failure Recovery
  • Hands-on: Building an Automated ML Pipeline
3.6 Model Deployment and Serving LAB
  • Batch and Online Inference
  • Model Serialization with Pickle and Joblib
  • ONNX and SavedModel Fundamentals
  • REST APIs with FastAPI
  • Model Serving Architectures
  • Dockerized Model Deployment
  • Kubernetes-Based Model Serving
  • Autoscaling and Load Balancing
  • Hands-on: Deploying an ML Model as a Microservice
3.7 ML CI/CD and Continuous Training
  • Continuous Integration for ML
  • Continuous Training Pipelines
  • Model Validation Gates
  • Automated Retraining Triggers
3.8 Model Monitoring and Reliability
  • Data and Concept Drift Detection
  • Model Performance Monitoring
  • Alerting and Incident Response
3.9 ML Testing and Production Reliability
  • Unit, Integration and End-to-End Testing
  • Model Testing Strategies
  • Production Reliability Patterns
Module 4: Cloud MLOps with AWS
4.1 AWS Foundations for MLOps
  • AWS Core Services for ML Workloads
  • IAM, VPC, S3, EC2, Lambda
  • Cost Management and Tagging
4.2 Amazon SageMaker AI
  • SageMaker Studio and Notebooks
  • Training Jobs and Hyperparameter Tuning
  • SageMaker Endpoints and Model Deployment
4.3 AWS ML Automation
  • SageMaker Pipelines
  • Step Functions for ML Orchestration
  • Event-Driven ML Workflows
4.4 Production AWS MLOps
  • Multi-Account Strategies
  • Security and Compliance on AWS
  • Monitoring with CloudWatch and SageMaker Model Monitor
Module 5: LLMOps — Large Language Model Operations
5.1 LLM Fundamentals
  • Transformer Architecture
  • Tokenization and Context Windows
  • Foundation Models Overview
5.2 Prompt Engineering
  • Zero-shot, Few-shot, Chain-of-Thought
  • Prompt Templates and Versioning
  • Structured Outputs
5.3 Embeddings and Vector Search
  • Embedding Models
  • Vector Databases (Pinecone, Weaviate, Chroma)
  • Similarity Search
5.4 Retrieval-Augmented Generation (RAG)
  • RAG Architecture
  • Chunking Strategies
  • Evaluation of RAG Systems
5.5 LLM Fine-Tuning
  • LoRA and QLoRA
  • Instruction Tuning
  • Evaluation Metrics
5.6 LLM Deployment and Inference
  • vLLM, TGI, TensorRT-LLM
  • Quantization
  • Serving Frameworks
5.7 LLMOps Pipelines
  • Prompt and Model Versioning
  • Evaluation Pipelines
  • Continuous Improvement
5.8 LLM Monitoring and Observability
  • Latency, Cost, and Quality Monitoring
  • LangSmith / Arize / Phoenix
5.9 Responsible AI and Guardrails
  • Content Filtering
  • Bias and Safety
  • Guardrail Frameworks
5.10 Amazon Bedrock for GenAI
  • Bedrock Agents
  • Knowledge Bases
  • Guardrails
Module 6: AI Agents and Autonomous Systems
6.1 AI Agent Fundamentals
  • Agent Loop (Perceive → Reason → Act)
  • Tools and Memory
6.2 Agent Frameworks
  • LangChain, LlamaIndex, CrewAI, LangGraph
  • AutoGen
6.3 Tool Use and Function Calling
  • Function Calling Patterns
  • Tool Selection and Error Handling
6.4 Model Context Protocol (MCP)
  • MCP Architecture
  • Building MCP Servers
  • Connecting Agents to Tools
6.5 Agent Memory and Knowledge
  • Short-term and Long-term Memory
  • Knowledge Graphs
6.6 Agent Planning and Reasoning
  • ReAct, Plan-and-Execute
  • Tree of Thoughts
6.7 Multi-Agent Systems
  • Orchestration Patterns
  • Agent Collaboration
6.8 Agent Evaluation and Testing
  • Evaluation Frameworks
  • Reliability Testing
6.9 Enterprise AI Agent Deployment
  • Security and Access Control
  • Observability for Agents
  • Production Deployment Patterns
Module 7: AIOps — AI for IT Operations
7.1 AIOps Fundamentals
  • What is AIOps
  • Use Cases in IT Operations
7.2 IT Telemetry and Data Collection
  • Metrics, Logs, Traces, Events
  • Observability Pipelines
7.3 Statistical Anomaly Detection
  • Statistical Methods
  • ML-based Anomaly Detection
7.4 Predictive Analytics and Forecasting
  • Time Series Forecasting
  • Capacity Planning
7.5 Intelligent Alerting and Event Correlation
  • Alert Noise Reduction
  • Event Correlation
7.6 Root Cause Analysis (RCA)
  • Automated RCA Techniques
  • Causal Inference
7.7 Self-Healing Infrastructure
  • Automated Remediation
  • Runbooks and Playbooks
7.8 Cloud-Native AIOps
  • Kubernetes Observability
  • Cloud-native AIOps Platforms
7.9 GenAI-Powered AIOps
  • LLM-assisted Incident Management
  • Natural Language Querying of Telemetry
Module 8: Production AI Security, Governance and Reliability
8.1 AI and ML Security
  • Model Theft and Inversion Attacks
  • Adversarial Examples
  • Data Poisoning
8.2 AI Application Security
  • Prompt Injection
  • Secure API Design
  • Secrets Management
8.3 Production Reliability
  • SLOs for AI Systems
  • Chaos Engineering for ML
  • Failover and Rollback Strategies
8.4 AI Governance and Compliance
  • Model Documentation and Cards
  • Bias Auditing
  • Regulatory Considerations
Module 9: Real-World Capstone Projects
Project 1: End-to-End MLOps Platform

Build a complete MLOps platform with data versioning, experiment tracking, model registry, automated pipelines, and production deployment.

Project 2: Production LLM Application with RAG

Design and deploy a production-grade RAG system with evaluation, monitoring, and guardrails.

Project 3: AIOps Monitoring and Self-Healing Platform

Create an AIOps system that detects anomalies, correlates events, and automates remediation.

Project 4: Enterprise DevOps AI Agent with MCP

Build an enterprise AI agent that integrates with real tools via MCP for operational automation.

Prerequisites

Basic programming knowledge (Python preferred), familiarity with command line, and a willingness to build production systems. Freshers are welcome.

Book a Mentorship Session Explore AI Automation Course