Professional Certificate in AI/ML & LLM Engineering for Developers

Python for AI Development

Build the programming foundation required for AI and Machine Learning development.

• Topics
  • Advanced Python
  • Object-Oriented Programming (OOP)
  • Data Structures & Algorithms
  • NumPy
  • Pandas
  • APIs
  • Asynchronous Programming
  • Git & GitHub
  • Virtual Environments
• Hands-On Projects
  • Build reusable Python libraries
  • REST API integration
  • Data processing pipelines

Mathematics for Machine Learning

Develop the mathematical foundation required to understand and build Machine Learning models.

• Topics
  • Linear Algebra
  • Probability & Statistics
  • Calculus
  • Optimization
  • Gradient Descent
• Hands-On Project
  • Implement Gradient Descent from scratch

Machine Learning

Learn the fundamental algorithms and techniques used to build predictive Machine Learning models.

• Topics
  • Data Preprocessing
  • Feature Engineering
  • Regression
  • Classification
  • Clustering
  • Decision Trees
  • Random Forest
  • Support Vector Machines (SVM)
  • K-Nearest Neighbors (KNN)
  • Naïve Bayes
  • Model Evaluation
  • Hyperparameter Tuning
  • Scikit-learn
  • XGBoost
  • LightGBM
• Hands-On Projects
  • Customer Churn Prediction
  • Loan Approval Prediction
  • House Price Prediction

Deep Learning

Understand neural networks and the deep learning architectures used in modern AI applications.

• Topics
  • Neural Networks
  • TensorFlow
  • Keras
  • PyTorch
  • Convolutional Neural Networks (CNN)
  • Recurrent Neural Networks (RNN)
  • LSTM
  • GRU
  • Attention
  • Transformers
• Hands-On Projects
  • Image Classification
  • Sentiment Analysis
  • Object Detection

Natural Language Processing (NLP)

Learn how AI systems process, understand and work with human language.

• Topics
  • Text Cleaning
  • Tokenization
  • Embeddings
  • Word2Vec
  • GloVe
  • TF-IDF
  • Named Entity Recognition (NER)
  • spaCy
  • NLTK
  • Hugging Face
• Hands-On Projects
  • Text Classification
  • Question Answering

Large Language Models (LLMs)

Understand the architecture and ecosystem behind modern Large Language Models.

• Topics
  • Transformer Architecture
  • Self-Attention
  • Tokenization
  • Embeddings
  • Context Windows
  • Llama
  • Mistral
  • Qwen
  • Gemma
  • Phi
  • Hugging Face Ecosystem
• Hands-On Projects
  • Run open-source LLMs locally
  • Benchmark LLM models

Building & Fine-Tuning Your Own LLM

Learn the techniques used to adapt open-source Large Language Models for specialized applications.

• Topics
  • Dataset Preparation
  • Instruction Tuning
  • Supervised Fine-Tuning
  • LoRA
  • QLoRA
  • PEFT
  • Quantization
  • Model Compression
  • DeepSpeed
  • Accelerate
• Hands-On Project
  • Fine-tune an open-source LLM

Retrieval-Augmented Generation (RAG)

Learn how to build AI applications that combine LLMs with external knowledge sources.

• Topics
  • Embeddings
  • FAISS
  • ChromaDB
  • Pinecone
  • Milvus
  • Chunking
  • Hybrid Search
  • Reranking
• Hands-On Projects
  • Enterprise PDF Chatbot
  • Knowledge Assistant

AI Agents

Learn to build intelligent AI agents capable of using tools, maintaining memory and executing multi-step tasks.

• Topics
  • LangChain
  • LangGraph
  • CrewAI
  • AutoGen
  • OpenAI Agents SDK
  • Tool Calling
  • Memory
  • Planning
  • Multi-Agent Systems
• Hands-On Projects
  • Coding Assistant
  • SQL Agent
  • Research Agent

Model Context Protocol (MCP)

Learn how AI applications can connect with external tools, databases and systems using MCP.

• Topics
  • MCP Architecture
  • MCP Servers
  • MCP Clients
  • Tool Registration
  • Database Integration
  • Browser Automation
• Hands-On Project
  • MCP Business Assistant

MLOps & AI Application Deployment

Learn how to deploy and operate AI applications using modern cloud and MLOps technologies.

• Topics
  • FastAPI
  • Docker
  • Kubernetes
  • MLflow
  • CI/CD
  • AWS
  • Azure AI
  • Google Cloud Vertex AI
• Hands-On Project
  • Deploy an LLM as a REST API

AI Security & Responsible AI

Learn essential practices for developing secure, reliable and responsible AI applications.

• Topics
  • Prompt Injection Protection
  • AI Guardrails
  • PII Protection
  • Hallucination Detection
  • Governance
  • Model Evaluation

Capstone Projects

Apply the concepts learned throughout the program by building end-to-end AI applications.

• Custom Fine-Tuned LLM
• Enterprise RAG Chatbot
• AI Coding Assistant
• Multi-Agent Business Automation
• AI Research Assistant
• Document Intelligence System
• Voice AI Assistant
• End-to-End Cloud Deployment

Tools & Technologies

• Python
• VS Code
• Jupyter Notebook
• Git
• NumPy
• Pandas
• Scikit-learn
• TensorFlow
• PyTorch
• Hugging Face
• LangChain
• LangGraph
• CrewAI
• AutoGen
• OpenAI Agents SDK
• FAISS
• ChromaDB
• Pinecone
• FastAPI
• Docker
• Kubernetes
• MLflow
• AWS
• Azure AI
• Google Cloud Vertex AI

Who Should Take This Course?

This program is designed for:

• Software Developers
• Python Developers
• Full-Stack Developers
• Data Engineers
• AI Enthusiasts
• Computer Science Students

It is particularly suited to learners who want to move beyond using AI tools and develop the technical capability to build AI/ML and LLM-powered applications.

Career Paths

The skills developed through this program can support career paths in areas such as:

• AI Engineering
• Machine Learning Engineering
• LLM Engineering
• Generative AI Development
• RAG Application Development
• AI Agent Development
• AI Application Development
• MLOps and AI Deployment