Master’s in Industrial Data & Platform MLOps Engineering
Online master's programme of 1,900 hours in industrial data engineering and platform MLOps: 12 modules covering OT/IT data, industrial connectivity, plant data modelling, industrial data platforms, AI models for operations, the MLOps lifecycle, model deployment, monitoring and AI governance, with an assigned technical tutor.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Integrate OT and IT data using industrial protocols and models.
Design edge-to-cloud industrial data platforms.
Build robust features from process signals.
Develop AI models for quality, processes and maintenance.
Implement reproducible, automated MLOps pipelines.
Deploy and monitor models in plant environments.
Govern industrial AI systems in line with European regulations.
Who it's for
- Industrial data engineers connecting OT systems to analytics platforms.
- MLOps engineers taking models from experimentation into production.
- IIoT architects designing edge-to-cloud data infrastructures.
- Process data scientists building soft sensors and quality models.
- ML platform engineers running shared infrastructure for data science teams.
- Industrial digital transformation leads driving AI adoption on the plant floor.
- Engineering or science graduates aiming to move into the chemical and petrochemical sector.
What you'll work with
- IEC 62264-1 (enterprise-control system integration, ISA-95)
- IEC 62541 (OPC Unified Architecture)
- Regulation (EU) 2024/1689 (AI Act) (European Artificial Intelligence Regulation)
- IEC 62443-3-3 (industrial cybersecurity: system security requirements)
- ISO/IEC 42001 (artificial intelligence management systems)
- ISO/IEC 23894 (AI risk management)
- IEC 61512-1 (batch control, ISA-88)
- IEC 63278-1 (Asset Administration Shell for industrial applications)
- MLflow
- Kubeflow
- Apache Kafka
- TimescaleDB
- Node-RED
12 modules · 1900 h
1.1The ISA-95 automation pyramid1.2OT systems: PLC, SCADA, DCS and historians1.3Convergence of IT and OT systems1.4Types of plant data: signals, events and batches1.5Sensor data quality1.6Process context and metadata1.7Latency and availability constraints1.8Industrial AI use cases1.9Organisational and cultural barriers1.10Case study: inventory of a plant's data sources
2.1OPC UA: information model and security2.2MQTT and Sparkplug B2.3Modbus and legacy protocols2.4Edge gateways and protocol conversion2.5Process historians2.6Unified Namespace architecture on the plant floor2.7Ingestion into cloud platforms2.8Buffering and tolerance to disconnections2.9Time synchronisation with PTP2.10Lab: Unified Namespace with MQTT and Sparkplug
3.1Equipment model according to ISA-953.2Batch models according to ISA-883.3Asset Administration Shell3.4Industrial ontologies and data semantics3.5Time series and asset context3.6Plant knowledge graphs3.7Quality data and genealogy3.8Integration with MES and ERP3.9Tag governance and naming conventions3.10Workshop: asset model with Asset Administration Shell
4.1Hybrid edge-cloud architectures4.2Time-series databases4.3Industrial lakehouse for process data4.4Commercial IIoT platforms4.5Kubernetes at the edge4.6Industrial stream processing4.7High-frequency storage4.8Cost and retention of sensor data4.9OT security according to IEC 624434.10Practical: time-series ingestion into TimescaleDB
5.1Signal cleaning and outliers5.2Resampling and time alignment5.3Time-domain and frequency-domain features5.4Process context variables5.5Feature stores for industrial data5.6Labelling events and failures5.7Imbalanced data in defects5.8Data leakage in time series5.9Time-series cross-validation5.10Lab: feature store with machine data
6.1Soft sensors and inference models6.2Product quality prediction6.3Process anomaly detection6.4Predictive maintenance models for equipment6.5Setpoint optimisation6.6Machine vision in inspection6.7Hybrid physics-data models6.8Interpretability for operators6.9Acceptance criteria on the plant floor6.10Case study: soft sensor for a distillation column
7.1The machine learning lifecycle7.2MLOps maturity levels7.3Experiment tracking7.4Data and model versioning7.5Model registry7.6Reproducibility and environments7.7Model and data testing7.8Continuous integration and delivery for ML7.9Documentation with model cards7.10Workshop: reproducible pipeline with MLflow and DVC
8.1Batch, online and edge inference8.2Container packaging8.3Model serving with KServe and Triton8.4Optimisation with ONNX and quantisation8.5Deployment on industrial edge devices8.6Canary, shadow and A/B deployments8.7Latency and real time on the plant floor8.8Integration with SCADA and MES8.9Rollback and version management8.10Practical: deploying an ONNX model at the edge
9.1Internal ML platform architecture9.2Kubeflow and pipeline orchestration9.3Feature stores on the platform9.4Compute and GPU management9.5Multi-tenancy and isolation9.6Self-service for data scientists9.7Templates and standards9.8ML cost and FinOps9.9Commercial versus open-source platforms9.10Lab: Kubeflow retraining pipeline
10.1Data drift and concept drift10.2Model degradation on the plant floor10.3Monitoring prediction quality10.4Automatic retraining and triggers10.5Alerting and incident management10.6Operator feedback10.7Pipeline observability10.8SLOs for ML services10.9Auditing and traceability10.10Workshop: drift detection in a quality model
11.1The European Artificial Intelligence Regulation11.2AI management according to ISO/IEC 4200111.3Risk management according to ISO/IEC 2389411.4Model security and OT cybersecurity11.5The Machinery Regulation and safety components11.6Ownership and sharing of industrial data11.7Ethics and human oversight11.8Required technical documentation11.9Validation in regulated sectors11.10Case study: risks of an AI system on the plant floor
12.1Selecting the industrial case12.2Proposed data architecture12.3Data ingestion and modelling12.4Model development12.5End-to-end MLOps pipeline12.6Deployment and monitoring12.7Technical and business evaluation12.8Conclusions and scaling12.9Thesis report12.10Master's Thesis: defence before a panel
How you'll learn
100% online training on the SEIUM campus, with downloadable materials, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme fits around your job.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is MLflow, Kubeflow, Apache Kafka, TimescaleDB and Node-RED, in free, academic or evaluation versions. Real procedures are studied, such as deploying soft sensors in a process plant, an IIoT data platform with a Unified Namespace and a retraining pipeline with drift monitoring. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: IEC 62264-1, IEC 62541, Regulation (EU) 2024/1689 (AI Act), IEC 62443-3-3, ISO/IEC 42001, ISO/IEC 23894, IEC 61512-1, IEC 63278-1.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
- Internet connection and a computer capable of running the programme software.
- English sufficient to read technical standards.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with MLflow, Kubeflow, Apache Kafka, TimescaleDB and Node-RED, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.
A university degree in engineering, science or architecture (or equivalent professional experience), a computer able to run the software and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Master’s in HPC & GPU Engineering for Simulation and AI
Online master's programme of 1,900 hours in HPC and GPU engineering for simulation and AI. 12 modules covering GPU architecture, CUDA programming, performance portability, distributed computing,…
Master’s in Edge AI & TinyML Engineering
Online master's programme of 1,900 hours in edge AI and TinyML: 12 modules covering microcontrollers and embedded systems, efficient neural networks, model compression, frameworks and compilers,…
Master’s in Causality and Experimentation Engineering
Online master's programme of 1,900 hours in causality and experimentation: 12 modules covering causal frameworks, causal graphs, classical design of experiments, online A/B testing, complex experiments,…
More in Data, AI, Simulation & Analytics
All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships