Skip to content
Lagos CityComputer College
AI Engineering, Cloud & DevOpsSpecialist ProgrammeIntermediateAdmission open

Machine Learning Engineering

Train, evaluate and deploy machine learning models that solve real business problems.

Programme duration, fees, schedules and entry requirements are being confirmed by the college. Please contact admissions for the latest information.

Programme overview

Machine learning engineers build the models behind recommendations, fraud detection, forecasting and image recognition. This programme takes you through the full machine learning workflow: framing the problem, preparing data, training and tuning models, and deploying them as dependable services.

You will practise on realistic datasets, including examples relevant to Nigerian businesses such as customer churn, credit risk and demand forecasting.

Who it is for

  • Developers and analysts moving into machine learning
  • STEM graduates
  • Data professionals who want to deploy models

Recommended background

  • Python programming
  • Basic statistics

Curriculum

7 modules · 28 topics

Indicative curriculum. Final modules and schedule are confirmed at enrolment.

  1. 01The Machine Learning WorkflowFrom business question to model.
    • Problem framing
    • Data collection and labelling
    • Train/validation/test splits
    • Baselines
  2. 02Data Preparation & Feature EngineeringTurn raw data into useful signals.
    • Cleaning and missing values
    • Encoding and scaling
    • Feature selection
    • Pipelines
  3. 03Supervised LearningPredict outcomes from labelled data.
    • Linear and logistic regression
    • Decision trees and random forests
    • Gradient boosting
    • Hyperparameter tuning
  4. 04Unsupervised LearningDiscover structure in data.
    • Clustering
    • Dimensionality reduction
    • Anomaly detection
    • Customer segmentation
  5. 05Deep Learning EssentialsNeural networks for complex data.
    • PyTorch basics
    • Image classification
    • Text classification
    • Transfer learning
  6. 06Model DeploymentServe predictions reliably.
    • Model serialisation
    • Prediction APIs
    • Docker
    • Batch vs real-time inference
  7. 07ProjectAn end-to-end ML solution.
    • Dataset and problem
    • Model development
    • Deployment
    • Results presentation

What you will be able to do

  • Frame business problems as machine learning tasks
  • Prepare data and engineer features with reproducible pipelines
  • Train, tune and evaluate supervised and unsupervised models
  • Deploy models as APIs inside containers

Tools & technologies

  • Python
  • pandas
  • scikit-learn
  • XGBoost
  • PyTorch
  • MLflow
  • FastAPI
  • Docker

Career paths

  • Machine Learning Engineer
  • Data Scientist
  • AI Engineer

Entry requirements

  • Specific entry requirements will be published once confirmed by the school.
  • Programme suitability depends on the individual course. Contact the admissions team for guidance.
Read the full admissions guide

Related programmes

  • AI Engineering, Cloud & DevOpsIntermediate to Advanced
    Professional Diploma Admission open

    AI Engineering

    Design, build and deploy production AI systems, from machine learning models to LLM-powered applications and AI agents.

    Learn more
  • AI Engineering, Cloud & DevOpsIntermediate
    Specialist Programme Admission open

    Generative AI & LLM Application Development

    Build chatbots, assistants and document-intelligence tools powered by large language models.

    Learn more
  • AI Engineering, Cloud & DevOpsBeginner
    Professional Course Admission open

    Python for AI & Data

    Learn Python from scratch and use it to analyse data, automate tasks and prepare for AI work.

    Learn more