School of Artificial Intelligence & Generative AI · Intermediate
Machine Learning Engineering Course
Move beyond notebook models and learn the engineering workflow employers expect: features, evaluation, APIs, deployment and monitoring.
Talk to an adviser on WhatsApp
ML Problem Framing and Experiment DesignFeature Engineering and Data PipelinesRegression EngineeringClassification Engineering
Pythonscikit-learnMLflowpandasimbalanced-learn
How you will learn
What you will learn, module by module
Learn supervised, unsupervised, and applied ML with model evaluation and deployment. Progress from ML Problem Framing and Experiment Design to Monitoring, Responsible ML and Capstone through guided labs, assessed projects, and portfolio evidence.
01Module 1 · 6 hoursML Problem Framing and Experiment DesignTurn three business cases into ML problem statements with metrics, baselines and validation plans.
Topics you will cover
- Business-to-ML translation
- Target definition
- Leakage prevention
- Baselines
- Offline versus online metrics
- Experiment tracking plan
- Reproducibility
- Tools and platforms
- Python, scikit-learn, MLflow
- Portfolio evidence
- ML problem-framing document
- Assessment
- Case-study assessment
02Module 2 · 8 hoursFeature Engineering and Data PipelinesBuild a reusable preprocessing pipeline for mixed numeric, categorical and temporal data.
Topics you will cover
- Missing data
- Categorical encoding
- Scaling
- Text/date features
- Feature selection
- Pipelines
- Class imbalance
- Data leakage controls
- Tools and platforms
- pandas, scikit-learn, imbalanced-learn
- Portfolio evidence
- Reusable feature pipeline
- Assessment
- Pipeline lab
03Module 3 · 8 hoursRegression EngineeringBenchmark multiple regression models for demand or price prediction.
Topics you will cover
- Linear models
- Regularisation
- Tree ensembles
- Gradient boosting
- Loss functions
- Residual diagnostics
- Business metrics
- Uncertainty awareness
- Tools and platforms
- scikit-learn, XGBoost/LightGBM
- Portfolio evidence
- Regression comparison notebook
- Assessment
- Model benchmark report
04Module 4 · 10 hoursClassification EngineeringBuild and tune a fraud, churn or lead-conversion classifier with threshold optimisation.
Topics you will cover
- Logistic regression
- Trees
- Random forests
- Boosting
- Probability calibration
- Threshold tuning
- ROC/PR curves
- Cost-sensitive classification
- Tools and platforms
- scikit-learn, XGBoost/LightGBM
- Portfolio evidence
- Decision-focused classifier
- Assessment
- Classification lab
05Module 5 · 8 hoursUnsupervised Learning and RepresentationCreate customer segments and anomaly flags, then explain business use cases.
Topics you will cover
- Clustering
- Dimensionality reduction
- Anomaly detection
- Similarity
- Segmentation
- PCA
- Practical evaluation without labels
- Tools and platforms
- scikit-learn, UMAP optional
- Portfolio evidence
- Segmentation analysis
- Assessment
- Segmentation checkpoint
06Module 6 · 10 hoursModel Evaluation, Tuning and ExplainabilityCompare candidate models using cross-validation, SHAP, and structured error analysis.
Topics you will cover
- Cross-validation
- Hyperparameter search
- Bias-variance
- Calibration
- Feature importance
- SHAP
- Fairness checks
- Error analysis
- Tools and platforms
- scikit-learn, Optuna, SHAP
- Portfolio evidence
- Model card + evaluation report
- Assessment
- Evaluation report
07Module 7 · 10 hoursPackaging, APIs and Production InferenceExpose a trained model as a validated REST API and containerise it.
Topics you will cover
- Serialisation
- FastAPI inference
- Request validation
- Batch versus online inference
- Docker basics
- Latency
- Versioning
- Logging
- Tools and platforms
- FastAPI, Pydantic, Docker
- Portfolio evidence
- Containerised ML API
- Assessment
- Deployment lab
08Module 8 · 14 hoursMonitoring, Responsible ML and CapstoneDeliver a production-style ML system with API, monitoring plan and model card.
Topics you will cover
- Data drift
- Model drift
- Performance monitoring
- Feedback loops
- Retraining triggers
- Governance
- Documentation
- Capstone architecture
- Tools and platforms
- MLflow, Evidently optional, Docker, GitHub
- Portfolio evidence
- Production ML engineering capstone
- Assessment
- Capstone demo and technical defence
Projects you will build
2 portfolio projects plus module evidence
Production Churn Prediction API
Train, tune, explain and deploy a churn classifier as an API.
ML pipeline · Model card · FastAPI endpoint · Dockerfile · Monitoring planRisk Scoring ML System
Develop a cost-sensitive classifier with threshold tuning and explainability.
Experiment report · SHAP analysis · API · Deployment architecture Course value
Why this course
Many ML learners can reproduce a notebook model but cannot design, evaluate, deploy, or explain a reliable end-to-end system.
The curriculum progresses from ML Problem Framing and Experiment Design to Monitoring, Responsible ML and Capstone, with guided labs, assessments, and two portfolio projects: Production Churn Prediction API and Risk Scoring ML System.
Who this course is for
Python users, analysts, data scientists and developers who want production-oriented ML skills.
IntermediateAI & Generative AI Engineer
PrerequisitesLearners should be comfortable with Python, pandas, and basic statistics.
What you will be able to do
- Turn three business cases into ML problem statements with metrics, baselines and validation plans.
- Build a reusable preprocessing pipeline for mixed numeric, categorical and temporal data.
- Benchmark multiple regression models for demand or price prediction.
- Build and tune a fraud, churn or lead-conversion classifier with threshold optimisation.
- Create customer segments and anomaly flags, then explain business use cases.
- Expose a trained model as a validated REST API and containerise it.
- Deliver a production-style ML system with API, monitoring plan and model card.
Technology you will use in this course
Pythonscikit-learnMLflowpandasimbalanced-learnXGBoostLightGBMUMAPOptunaSHAPFastAPIPydanticDockerEvidentlyGitHub
Career relevance
AI & Generative AI Engineer
This course supports the development of skills relevant to roles such as Machine Learning Engineer, Applied ML Engineer, and Junior Data Scientist. The strongest learner outcome is a portfolio that shows the problem, implementation, testing or evaluation, documentation and a clear explanation of decisions—not a certificate alone.
Course evidence and instruction
Discuss your learning pathway
Review prerequisites, learning format and project expectations with admissions before enrolment.
Get course guidanceExplore the course projects
Review the project briefs and deliverables to understand the work expected during the course.
Review project expectationsTechnology references
Technology names identify learning tools and do not imply an employer partnership or endorsement.
Microsoft
Clear answers before you enrol
Is the Machine Learning Engineering course suitable for beginners?
This is an intermediate-level course. Learners should be comfortable with Python, pandas, and basic statistics.
What will I build during the course?
You will complete guided labs in every module and build two portfolio projects: Production Churn Prediction API and Risk Scoring ML System. Deliverables include working files or code, documentation, testing or evaluation evidence, and a final presentation.
Which tools and platforms are covered?
Key tools include Python, scikit-learn, MLflow, pandas, imbalanced-learn, XGBoost, LightGBM, and UMAP. Additional platforms are introduced in relevant modules through practical tasks, and the toolset may evolve as industry practice changes.
How long does the course take?
The course includes approximately 74 guided learning hours across 8 modules, normally delivered over 10–12 weeks depending on batch intensity and learner practice time.
Which career paths can this course support?
The curriculum supports the development of skills relevant to roles such as Machine Learning Engineer, Applied ML Engineer, and Junior Data Scientist. Career outcomes depend on prior experience, project quality, interview readiness and market conditions; employment is not guaranteed.
Will I receive mentor and career support?
The course includes live instruction, lab support, assignment feedback, project reviews and career preparation covering portfolio development, CV writing, LinkedIn profile improvement, and interview guidance.
Ready to start?
A-56, Sector-64, Noida, Uttar Pradesh – 201301Ready to start your Machine Learning Engineering journey?
Review the full curriculum, experience a live class and confirm the right starting point before enrolling.