AI Engineer
Develop job-ready AI skills employers need. Build highly sought-after AI engineering skills and practical experience
About this Course:
An AI engineer designs AI systems that produce new data—like images, text, audio, and video—using transformers and LLMs.
This course covers the essential skills in gen AI, large language models (LLMs), and natural language processing (NLP) required to catch the eye of an employer. You will dive into AI, gen AI, and prompt engineering, along with data analysis, machine learning, and deep learning using Python. You'll work with libraries like SciPy and scikit-learn and build apps using frameworks and models such as BERT, GPT, and LLaMA. You'll use Hugging Face Transformers, PyTorch, RAG, and LangChain for developing and deploying LLM NLP-based apps, while exploring tokenization, language models, and transformer techniques.
You’ll also get plenty of practical experience in hands-on labs and projects that you can talk about in interviews. Plus, you’ll complete a significant guided project where you’ll create your own real-world gen AI application.
The hands-on work includes:
- Generating text, images, and code through gen AI
- Applying prompt engineering techniques and best practices
- Creating multiple gen AI-powered applications with Python and deploying them using Flask
- Creating an NLP data loader
- Developing and training a simple language model with a neural network
- Applying transformers for classification, and building and evaluating a translation model
- Performing prompt engineering and in-context learning
- Fine-tuning models to improve performance
- Using LangChain tools and components for different applications
- Building AI agents and applications with RAG and LangChain in a significant guided project.
Learning Objectives
Introduction to AI
- Explain the fundamental concepts and applications of AI in various domains.
- Describe the core principles of machine learning, deep learning, and neural networks, and apply them to real-world scenarios.
- Analyze the role of generative AI in transforming business operations, identifying opportunities for innovation and process improvement.
- Design a generative AI solution for an organizational challenge, integrating ethical considerations.
Gen AI: Introduction and Applications
- Describe generative AI and distinguish it from discriminative AI.
- Describe the capabilities of generative AI and its use cases in the real world.
- Identify the applications of generative AI in different sectors and industries.
- Explore common generative AI models and tools for text, code, image, audio, and video generation.
Gen AI: Prompt Engineering
- Explain the concept, relevance, and best practices of prompt engineering to guide generative AI models in producing meaningful, accurate outputs.
- Apply prompt engineering techniques to text prompts, improving the reliability and quality of large language models.
- Practice prompt engineering techniques and approaches, including interview pattern, chain-of-thought, tree-of-thought, to improve prompt outcomes.
- Explore commonly used tools for prompt engineering to aid with prompt engineering.
Python for Data Science, AI & Development
- Develop a foundational understanding of Python programming by learning basic syntax, data types, expressions, variables, and string operations.
- Apply Python programming logic using data structures, conditions and branching, loops, functions, exception handling, objects, and classes.
- Demonstrate proficiency in using Python libraries such as Pandas and Numpy and developing code using Jupyter Notebooks.
- Access and extract web-based data by working with REST APIs using requests and performing web scraping with BeautifulSoup.
Developing AI Applications with Python and Flask
- Describe the steps and processes involved in creating a Python application including the application development lifecycle
- Create Python modules, run unit tests, and package applications while ensuring the PEP8 coding best practices
- Build and deploy web applications using Flask, including routing, error handling, and CRUD operations.
- Create and deploy an AI-based application onto a web server using IBM Watson AI Libraries and Flask.
Building Generative AI-Powered Applications with Python
- Explain the core concepts of generative AI, including large language models, speech technologies, and platforms such as IBM watsonX, and Hugging Face
- Build generative AI-powered applications and chatbots using LLMs, retrieval-augmented generation(RAG), and foundational Python frameworks
- Integrate speech-to-text (STT) and text-to-speech (TTS) technologies to enable voice interfaces in generative AI applications
- Develop web-based AI
applications using Python libraries, such as Flask and Gradio, along with basic front-end tools like HTML, CSS, and JavaScript
Data Analysis with Python
- Construct Python programs to clean and prepare data for analysis by addressing missing values, formatting inconsistencies, normalization, and binning
- Analyze real-world datasets through exploratory data analysis (EDA) using libraries such as Pandas, NumPy, and SciPy to uncover patterns and insights
- Apply data operation techniques using dataframes to organize, summarize, and interpret data distributions, correlation analysis, and data pipelines
- Develop and evaluate regression models using Scikit-learn, and use these models to generate predictions and support data-driven decision-making
Machine Learning with Python
- Explain key concepts, tools, and roles involved in machine learning, including supervised and unsupervised learning techniques.
- Apply core machine learning algorithms such as regression, classification, clustering, and dimensionality reduction using Python and scikit-learn.
- Evaluate model performance using appropriate metrics, validation strategies, and optimization techniques.
- Build and assess end-to-end machine learning solutions on real-world datasets through hands-on labs, projects, and practical evaluations.
Introduction to Deep Learning & Neural Networks with Keras
- Describe the foundational concepts of deep learning, neurons, and artificial neural networks to solve real-world problems
- Explain the core concepts and components of neural networks and the challenges of training deep networks
- Build deep learning models for regression and classification using the Keras library, interpreting model performance metrics effectively.
- Design advanced architectures, such as CNNs, RNNs, and transformers, for solving specific problems like image classification and language modeling
Generative AI and LLMs: Architecture and Data Preparation
- Differentiate between generative AI architectures and models, such as RNNs, transformers, VAEs, GANs, and diffusion models
- Describe how LLMs, such as GPT, BERT, BART, and T5, are applied in natural language processing tasks
- Implement tokenization to preprocess raw text using NLP libraries like NLTK, spaCy, BertTokenizer, and XLNetTokenizer
- Create an NLP data loader in PyTorch that handles tokenization, numericalization, and padding for text datasets
Gen AI Foundational Models for NLP & Language Understanding
- Explain how one-hot encoding, bag-of-words, embeddings, and embedding bags transform text into numerical features for NLP models
- Implement Word2Vec models using CBOW and Skip-gram architectures to generate contextual word embeddings
- Develop and train neural network-based language models using statistical N-Grams and feedforward architectures
- Build sequence-to-sequence models with encoder–decoder RNNs for tasks such as machine translation and sequence transformation
Generative AI Language Modeling with Transformers
- Explain the role of attention mechanisms in transformer models for capturing contextual relationships in text
- Describe the differences in language modeling approaches between decoder-based models like GPT and encoder-based models like BERT
- Implement key components of transformer models, including positional encoding, attention mechanisms, and masking, using PyTorch
- Apply transformer-based models for real-world NLP tasks, such as text classification and language translation, using PyTorch and Hugging Face tools
Generative AI Engineering and Fine-Tuning Transformers
- Sought-after, job-ready skills businesses need for working with transformer-based LLMs in generative AI engineering
- How to perform parameter-efficient fine-tuning (PEFT) using methods like LoRA and QLoRA to optimize model training
- How to use pretrained transformer models for language tasks and fine-tune them for specific downstream applications
- How to load models, run inference, and train models using the Hugging Face and PyTorch frameworks
Generative AI Advance Fine-Tuning for LLMs
- In-demand generative AI engineering skills in fine-tuning LLMs that employers are actively seeking
- Instruction tuning and reward modeling using Hugging Face, plus understanding LLMs as policies and applying RLHF techniques
- Direct preference optimization (DPO) with partition function and Hugging Face, including how to define optimal solutions to DPO problems
- Using proximal policy optimization (PPO) with Hugging Face to build scoring functions and tokenize datasets for fine-tuning
Fundamentals of AI Agents Using RAG and LangChain
- In-demand, job-ready skills businesses seek for building AI agents using RAG and LangChain in just 8 hours
- How tapply the fundamentals of in-context learning and advanced prompt engineering timprove prompt design
- Key LangChain concepts, including tools, components, chat models, chains, and agents
- How tbuild AI applications by integrating RAG, PyTorch, Hugging Face, LLMs, and LangChain technologies
Project: Generative AI Applications with RAG and LangChain
- Gain practical experience building your own real-world generative AI application to showcase in interviews
- Create and configure a vector database to store document embeddings and develop a retriever to fetch relevant segments based on user queries
- Set up a simple Gradio interface for user interaction and build a question-answering bot using LangChain and a large language model (LLM)