Ippy, Central African Republic

Generative AI

Vertex AI on Google Cloudin Ippy

Explore machine learning and Generative AI with StepMerit's Vertex AI on Google Cloud course. Learn to build, train, evaluate, and deploy AI models using Google Cloud's managed machine learning platform. Develop practical knowledge of data…

40 Hours/5 daysLive virtual trainingIntermediate

Training is delivered live online for learners in Ippy, Central African Republic. Corporate programs are available for teams; request a quotation to confirm the schedule.

Plan your attendance

Training information for Ippy

Selected country and city time: Europe/London. Times follow the selected country and city. Choose another time zone below if needed.

Training information for Ippy
DeliveryLive online · Classroom when confirmed
Price$819 USD

Loading approximate local-currency equivalent…

Bookings and payments are in USD only.

ScheduleCourse-page batches starting in the next 7 days; subject to availability
Exam voucherCheck with StepMerit
Classroom venueClient premises or a StepMerit-arranged conference hall in Ippy, subject to venue and batch confirmation.
Weekend · 5 training days

Starts Nov 21, 2026, 9:00 AM

First session ends Nov 21, 2026, 3:00 PM

Europe/London · Weekend hours are flexible. Schedule and delivery subject to confirmation.

Enquire about this batch
Weekday · 5 training days

Starts Nov 23, 2026, 9:00 AM

First session ends Nov 23, 2026, 5:00 PM

Europe/London · Schedule and delivery subject to confirmation.

Enquire about this batch
Corporate batches

Chat with us on WhatsApp to arrange training for your team.

What you will learnExpand syllabus +

Module 1: Introduction to Google Cloud AI and Vertex AI

  • Google Cloud AI Fundamentals
    • Understand the role of cloud computing in modern artificial intelligence and machine learning solutions.
    • Explore Google Cloud AI services and their applications across enterprise environments.
  • Vertex AI Platform Overview
    • Understand Vertex AI architecture, key capabilities, and managed machine learning services.
    • Explore how Vertex AI supports the development, deployment, and management of AI models.

Module 2: Google Cloud Environment Setup

  • Google Cloud Project Configuration
    • Learn how to create and configure a Google Cloud project for AI development.
    • Understand billing, service enablement, identity management, and access permissions.
  • Vertex AI Workspace and Tools
    • Explore the Google Cloud Console, Vertex AI interfaces, and supported development environments.
    • Understand how notebooks and development tools support machine learning experimentation.

Module 3: Data Preparation and Management

  • Dataset Collection and Storage
    • Understand how structured and unstructured datasets support machine learning projects.
    • Explore Google Cloud Storage and relevant data services for organising training data.
  • Data Cleaning and Preprocessing
    • Learn techniques for handling missing values, inconsistent records, and data quality issues.
    • Understand data transformation and preparation for machine learning workflows.
  • Dataset Exploration
    • Explore data distributions, feature relationships, and potential data quality problems.
    • Understand how suitable training and evaluation datasets support reliable model assessment.

Module 4: Machine Learning with Vertex AI

  • Machine Learning Workflow Fundamentals
    • Understand the stages of machine learning, from problem definition to model evaluation.
    • Explore supervised and unsupervised learning use cases.
  • Vertex AI Training Options
    • Learn the fundamentals of managed training, custom training jobs, and supported model development approaches.
    • Understand how computing resources and training configurations affect experimentation.
  • Model Experimentation
    • Explore model configuration, parameter selection, and iterative experimentation.
    • Learn how to compare alternative model approaches using consistent evaluation criteria.

Module 5: AutoML and Custom Model Development

  • Introduction to AutoML
    • Understand how automated machine learning can simplify selected model development tasks.
    • Explore supported AutoML workflows and their suitability for different data problems.
  • Custom Model Training
    • Learn the basic workflow for preparing code, configuring training jobs, and running custom model experiments.
    • Understand when custom training may be appropriate for specialised machine learning requirements.
  • Model Selection
    • Compare automated and custom development approaches based on flexibility, data requirements, and project objectives.
    • Evaluate the trade-offs involved in selecting an appropriate model development strategy.

Module 6: Model Evaluation and Hyperparameter Tuning

  • Model Performance Assessment
    • Understand metrics such as accuracy, precision, recall, F1-score, and regression evaluation measures.
    • Learn how to interpret evaluation results based on the business problem and dataset characteristics.
  • Hyperparameter Optimisation
    • Explore how hyperparameter tuning can help identify suitable model configurations.
    • Understand experiment comparison and the importance of consistent evaluation datasets.
  • Model Validation
    • Learn how validation and independent testing help identify overfitting and generalisation issues.
    • Understand how to document model limitations and evaluation findings.

Module 7: Generative AI with Vertex AI

  • Foundation Models and Generative AI
    • Understand foundation models and their applications in text generation, summarisation, and question answering.
    • Explore how Vertex AI provides access to supported generative AI capabilities.
  • Prompt Design and Model Interaction
    • Learn how to structure prompts and evaluate generated responses for relevance and quality.
    • Understand the influence of context, instructions, and model settings on output behaviour.
  • Generative AI Application Development
    • Explore the architecture of applications that integrate foundation models with business data and application interfaces.
    • Understand responsible AI considerations, output validation, and safeguards against unsupported responses.

Module 8: Vertex AI Pipelines and MLOps

  • Machine Learning Pipeline Fundamentals
    • Understand how data preparation, training, evaluation, and model registration can be organised into repeatable workflows.
    • Explore the role of pipeline components in improving workflow consistency.
  • Pipeline Orchestration
    • Learn the basic principles of defining, running, and monitoring machine learning pipelines.
    • Understand how automation can support repeatable model development and testing.
  • MLOps Practices
    • Explore version control, experiment tracking, model lineage, and lifecycle management concepts.
    • Understand how operational practices support collaboration and maintainability.

Module 9: Model Deployment and Prediction

  • Model Deployment Fundamentals
    • Understand how trained models can be deployed to supported Vertex AI endpoints.
    • Explore deployment configuration, resource allocation, and endpoint management.
  • Online and Batch Prediction
    • Compare online prediction requests with batch inference workflows.
    • Understand how workload requirements influence prediction methods.
  • Application Integration
    • Explore how APIs can connect deployed models with applications and business systems.
    • Learn basic concepts for managing requests, responses, authentication, and access permissions.

Module 10: Model Monitoring and Responsible AI

  • Model and Endpoint Monitoring
    • Understand monitoring concepts for deployed models, prediction traffic, and operational performance.
    • Explore how logs and metrics can help identify operational issues.
  • Model Quality and Drift
    • Learn the concepts of data drift and prediction drift and why ongoing evaluation matters.
    • Understand how changes in input data may affect model performance over time.
  • Security and Responsible AI
    • Explore identity and access management, data protection, and secure AI development practices.
    • Understand fairness, transparency, explainability, and human oversight considerations.

Module 11: Capstone Project – End-to-End AI Solution on Vertex AI

  • Project Planning and Data Preparation
    • Define a practical business problem, select an appropriate dataset, and prepare data for model development.
    • Document project objectives, evaluation criteria, and data quality requirements.
  • Model Development and Evaluation
    • Train or configure a suitable model using an appropriate Vertex AI workflow.
    • Evaluate model performance and document findings, limitations, and potential improvements.
  • Deployment and Demonstration
    • Deploy the model using a suitable supported approach and demonstrate its prediction workflow.
    • Present the solution architecture, implementation decisions, security considerations, and future enhancements.

Module 12: Project Review and Practical Assessment

  • Implementation Review
    • Review the completed project for workflow consistency, model quality, and deployment considerations.
    • Identify technical challenges and possible optimisation opportunities.
  • Knowledge Assessment
    • Evaluate understanding of Vertex AI services, machine learning workflows, generative AI, MLOps, and monitoring.
    • Practise applying course concepts to realistic cloud AI scenarios.
  • Project Documentation
    • Prepare a technical report covering the architecture, data preparation, model evaluation, deployment, and limitations.
    • Present project outcomes and recommendations for future development.

StepMerit will make the necessary arrangements to provide the required lab environment. Lab costs, where applicable, will be charged separately.

Exam details

  • Exam Level: Intermediate – Vertex AI on Google Cloud.
  • Exam Type: Online computer-based assessment featuring multiple-choice questions and scenario-based questions.
  • Number of Questions: 40 questions.
  • Exam Duration: 90 minutes.
  • Proposed Passing Score: 70% (28 out of 40 questions).
  • Exam Language: English.
  • Practical Knowledge Assessment: Scenario-based questions covering model development, prediction workflows, pipeline orchestration, endpoint management, and monitoring concepts.
  • Evaluation Criteria: Learners are assessed on technical understanding, model evaluation, cloud AI workflow selection, troubleshooting, and responsible AI practices.
  • Certification: Eligible learners may receive a StepMerit course-completion certificate after meeting the applicable course and assessment requirements. Google Cloud professional certification is separate.
  • Exam Preparation: Review Vertex AI services, machine learning fundamentals, model training and evaluation, generative AI workflows, pipeline management, deployment, monitoring, and security.
  • Training and Assessment Support: StepMerit provides structured learning and assessment preparation through its Vertex AI on Google Cloud training in Ippy, Central African Republic.

Plan your learning

Who this course is for

AI and Machine Learning Engineers Data Scientists and Data Analysts Google Cloud Professionals Python Developers Machine Learning Practitioners Generative AI Developers MLOps Engineers Cloud Architects and Cloud Engineers Software Developers and AI Application Developers IT Professionals and Technical Consultants

Before you begin

Basic Computer Skills: Ability to use digital applications, manage files, and navigate online platforms. Cloud Computing Fundamentals: Basic understanding of cloud services, infrastructure, and cloud-based application environments. Google Cloud Platform Awareness: Familiarity with Google Cloud concepts and services is beneficial but not mandatory for introductory learning. Python Programming Basics: Understanding variables, functions, data structures, and basic Python syntax is recommended for practical exercises. Machine Learning Fundamentals: Basic awareness of machine learning algorithms, training workflows, and model development. Data Preparation Skills: Familiarity with datasets, data…

Learning outcomes

Problem Statement: Improving Healthcare Risk Prediction A hypothetical healthcare organisation manages large volumes of patient records, laboratory results, medical histories, and appointment data. Healthcare administrators want to explore how machine learning can help identify patients who may require additional follow-up based on historical, appropriately authorised data. However, preparing datasets, training predictive models, evaluating performance, and managing deployment workflows can be technically challenging. The learning challenge is to develop a prototype machine learning solution using Google Cloud Vertex AI that demonstrates the model development lifecycle while addressing data…

Related reading

Course blogs for learners in Ippy

Explore this course locally

Know the location

Local information: Ippy

Ippy, Central African Republic. View city location ↗

City overview

Ippy, Central African Republic.

Geography & administration

Time zone: Europe/London.

Education & learning

Course learning optionsExplore Vertex AI on Google Cloud through live online instructor-led training. Ippy learners can request a corporate program for their teams. Course duration: 40 Hours/5 days. Check the upcoming online batches and contact StepMerit to confirm the schedule and exam arrangements.