IBM Generative AI Engineering (berufsbezogenes Zertifikat)

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.

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.

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.

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

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

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

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.

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

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

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

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

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

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

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

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)