AI Engineering

About this internship

Curriculum

1. 1. Introduction to Machine Learning with NLP

   🐍 Python Programming
   Work with Python for AI development.
   Read and manipulate datasets.
   📊 Data Preprocessing
   Load datasets using Pandas.
   Clean and preprocess text data.
   Handle missing values and prepare data for training.
   🧠 Machine Learning Fundamentals
   Understand what supervised learning is.
   Learn features, labels, training data, and test data.
   Split datasets into training and testing sets.
   ✨ Natural Language Processing (NLP)
   Tokenization
   Stop-word removal
   Text vectorization (e.g., TF-IDF)
   Converting human language into numerical features.
   🤖 Model Training
   Train a sentiment classification model.
   Compare algorithms such as Logistic Regression or Naive Bayes.
   Evaluate model performance.
   📈 Model Evaluation
   Accuracy
   Precision
   Recall
   F1 Score
   Confusion Matrix
   💾 Model Serialization
   Save the trained model using Pickle or Joblib.
   Load the model for future predictions.
   🔌 Backend Development
   Build an AI prediction API using FastAPI or Flask.
   Accept user input and return model predictions.
   🎨 Frontend Development
   Build a clean user interface.
   Connect the frontend with the backend using HTTP requests.
   🌐 Deployment
   Deploy the AI application so others can use it online.
   📂 Software Engineering Skills
   Organize project folders.
   Use Git and GitHub.
   Write a README and document the project.

   Includes a knowledge assessment

2. 2. Conversational AI and Healthcare Chatbot Development

   In this module, you will learn how to build a domain-specific AI chatbot and integrate it into an existing business website.

   You will develop an AI assistant for Rashid Dental Clinic. The chatbot will answer questions using clinic-approved Markdown files, provide information about dental services, collect appointment requests, and direct users toward clinic staff when human assistance is required.

   The chatbot must act as an informational and appointment-support assistant. It must never diagnose dental conditions, prescribe medicines, recommend dosages, or replace a qualified dentist.

   Learning Outcomes

   After completing this module, you should be able to:

   • Understand conversational AI architecture
   • Create system prompts and chatbot guardrails
   • Build a Markdown-based knowledge base
   • Generate and store vector embeddings
   • Implement Retrieval-Augmented Generation
   • Develop chatbot APIs using FastAPI
   • Integrate a chatbot widget into a website
   • Collect and store appointment requests
   • Protect private user information
   • Test chatbot accuracy, safety, and reliability
   • Deploy a complete AI chatbot application

   Includes a knowledge assessment

3. 3. Guided Project: Build and Deploy an Ollama Cloud AI Agent with LangChain, LangGraph, FastAPI and Render

   In this guided project, you will build a complete AI agent using Python.

   Your AI agent will use a cloud-hosted Ollama model, such as Qwen, and will be deployed publicly on Render.

   You will learn how to:

   Use an Ollama Cloud API key
   Select and use a cloud AI model such as Qwen
   Use LangChain to communicate with the AI model
   Use LangGraph to create an agent workflow
   Build an API with FastAPI
   Test APIs through Swagger documentation
   Secure API keys with environment variables
   Deploy a FastAPI AI agent on Render for free

   By the end, you will have a public AI-agent API that can be used by a website, mobile application, or frontend chatbot.

   Includes a knowledge assessment

Guidelines and requirements