GEN AI & LLM ENGINEER

2591 Dallas Pkwy, Suite 300 Frisco, TX 75034, USA
info@bicourses.com

Follow Us On:

GEN AI & LLM ENGINEER

GEN AI & LLM ENGINEER

Course Description

Prerequisite: IT Professionals with Strong Python (or any language) Coding Skills, Mathematical and Statistical Expertise, SQL/Database Experience, Cloud Platform Knowledge, and Good Communication Skills.

Job Prospects: GEN AI & LLM ENGINEER

COURSE-1: PYTHON - QUICK RECAP (10 Sessions)

MODULE-1: PYTHON FUNDAMENTALS

Python Installation (Windows / Mac)
Variables and Data Types
Operators
Conditional Statements & Loops
Functions
File Handling
Exceptional Handling

MODULE-2: DATA STRUCTURES

Lists
Dictionaries
Tuples
Sets

MODULE-3: OBJECT-ORIENTED PROGRAMMING

Classes, Objects and Methods
Inheritance and Polymorphism
Abstraction and Encapsulation

MODULE-4: ADVANCED PYTHON

Decorators
Packages and Modules
API Development (Flask)
SQL, MySQL and SQLite Overview

MODULE-5: PYTHON LIBRARIES

NumPy
Pandas
Matplotlib
Scikit

COURSE-2: Data Modeling Introduction (5 Sessions)

MODULE-1: EDA-EXPLORATORY DATA ANALYSIS WITH THE DATASET

Understanding Data Distribution
Identifying Missing Values
Handling Outliers
Data Visualization Techniques
Feature Selection

MODULE-2: UNDERSTANDING MODEL METRICS

Introduction to Model Metrics
Classification Metrics (Accuracy, Precision, Recall, F1-Score, ROC Curve and AUC)
Regression Metrics (MAE, MSE, RMSE & R-Squared)
Clustering Metrics (Silhouette Score, Davies-Bouldin Index, Inertia)

MODULE-3: VECTOR DATABASE

Introduction to Vector Databases (e.g., Pinecone, Milvus)
Use Cases in Natural Language Processing (NLP) (e.g., Semantic Search, Recommendation Systems)
Hands-on with a Vector Database (e.g., Using Python to interact with a Vector DB)

COURSE-3: ARTIFICIAL INTELLIGENCE (AI) INTRODUCTION (10 SESSIONS)

MODULE-1: MACHINE LEARNING (ML) CONCEPTS

Supervised Learning (Linear, Logistic Regression)
Unsupervised Learning (K-means & DBSCAN Clustering)
Reinforcement Learning (Q-Learning)
Identifying the Suitable ML Algorithm
Implementation Using Scikit-learn

MODULE-2: DEEP LEARNING (DL) CONCEPTS

Neurons, Perceptrons
Layers
Activation Functions
Forward Propagation, Back Propagation
Loss Functions, Optimization

MODULE-3: TENSORFLOW BASICS

Building and Training Models
TensorFlow Keras API
Hands-on with TensorFlow for Basic Models
Introduction to TensorFlow Datasets
Custom Training Loops and Saving Models

MODULE-4: DEEP LEARNING NEURAL NETWORKS

Basics of Convolutional Neural Network (CNN)
Introduction to Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM) & Gated Recurrent Unit (GRU)
Introduction to Natural Language Processing (NLP)
Text Preprocessing Techniques
Key NLP Tasks and Examples
Word Embeddings

COURSE-4: CLOUD PLATFORM (AWS) INTRODUCTION (2 SESSIONS)

MODULE-1: AMAZON WEB SERVICES (AWS) FUNDAMENTALS

Overview of AWS
AWS Compute and Storage Services
AWS Database Services
Deployment and Management Tools
Monitoring, Security, and Cost Management

MODULE-2: BUILDING MODEL USING SAGEMAKER

Introduction to Amazon SageMaker
Setting Up SageMaker
Preparing Data
Building and Training Models
Deploying and Managing Models

COURSE-5: GEN AI & LARGE LANGUAGE MODELS (LLMS) (13 SESSIONS)

MODULE-1: TRANSFORMERS

Building Transfomers Models & Architecture
Encoder & Decoder Architectures
Attention Mechanisms, Self Attention and Multi-Head Attention
Position-Wise Feed-Forward Networks (FFN)
Transfer Learning with Transformers

MODULE-2: LARGE LANGUAGE MODELS (LLMs)

Key Concepts of LLMs
Introduction to Generative Pre-trained Transformer (GPT)
Introduction to Bidirectional Encoder Representations from Transformers (BERT)
Introduction to Text-to-Text Transfer Transformer (T5)
Evaluation Metrics

MODULE-3: GENERATIVE ARTIFICIAL INTELLIGENCE (GEN AI)

Key Concepts of GenAI
Introduction to Generative Adversarial Networks (GAN)
Introduction to Variational AutoEncoders (VAE)
Text Generation Techniques

MODULE-4: RETRIEVAL-AUGMENTED GENERATION (RAG)

Introduction to RAG
Retrieval Mechanism
Generation Techniques
Fusion Techniques
Evaluation Metrics

STUDENT ASSIGNMENTS

Build an ML Loan Prediction Model with Linear Regressionn
Build an ML Classification Model using Logistic Regression
Build a DL Model for Next Word Generation
Build a DL Model for Text Summarization
Build a DL Model for Sentimental Analysis
Mini-Project to Build a Chatbot

PRACTICE PLATFORM

Google Colab
Kaggle
AWS

Fee - $600

Enroll Now

Classes

~50 Hours
Assignments

~80 Hours
Duration

~10 Weeks

Share On: