Postgraduate Diploma in MLOps Infrastructure for Insurance
Online Postgraduate Diploma of 800 h in MLOps infrastructure for Insurance. 8 modules covering Regulation (EU) 2024/1689 (Artificial Intelligence Act), Regulation (EU) 2022/2554 (DORA) and MLflow. Personal tutor assigned and enrolment open.
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
Describe the lifecycle of predictive models in an insurer.
Design reproducible data pipelines for machine learning.
Manage experiments, versions and model registries.
Package and orchestrate models using containers.
Deploy models into production in batch and real-time modes.
Monitor the drift and performance of deployed models.
Integrate governance, risk and compliance requirements into the platform.
Who it's for
- MLOps engineer who wants to specialise in MLOps Infrastructure for Insurance.
- Machine learning engineer who wants to specialise in MLOps Infrastructure for Insurance.
- Data platform architect who wants to specialise in MLOps Infrastructure for Insurance.
- Insurance data scientist who wants to specialise in MLOps Infrastructure for Insurance.
- Model risk manager who wants to specialise in MLOps Infrastructure for Insurance.
- DevOps engineer who wants to specialise in MLOps Infrastructure for Insurance.
- Engineering or science graduates seeking to enter insurance companies.
What you'll work with
- Regulation (EU) 2024/1689 (Artificial Intelligence Act)
- Regulation (EU) 2022/2554 (DORA)
- ISO/IEC 42001 (artificial intelligence management systems)
- ISO/IEC 5338 (AI system lifecycle processes)
- ISO/IEC 23894 (AI risk management)
- ISO/IEC 27001 (information security)
- Regulation (EU) 2016/679 (GDPR)
8 modules · 800 h
1.1Machine learning use cases in underwriting and claims1.2Differences between DevOps and MLOps1.3MLOps maturity levels1.4Roles: data scientist, ML engineer and actuary1.5Requirements for actuarial models in production1.6Technical debt in ML systems1.7Reference MLOps architecture1.8Open source and managed tools1.9Model governance in insurers1.10Case study: model map of an insurer
2.1Ingestion pipelines for policies and claims2.2Data lakes and lakehouses with Delta Lake2.3Data quality with Great Expectations2.4Feature stores: Feast and alternatives2.5Data versioning with DVC2.6Sensitive data and anonymisation2.7Data lineage and catalogue2.8Batch processing with Spark2.9Streaming with Kafka for telematics2.10Laboratory: feature store for claims frequency variables
3.1Experiment tracking with MLflow3.2Environment reproducibility3.3Distributed training and GPUs3.4Hyperparameter optimisation3.5Model registration and metadata3.6GLM, GBM and neural network models3.7Temporal validation on insurance data3.8Unit testing for ML code3.9Code review and best practices3.10Practical: registering a frequency model in MLflow
4.1Docker for packaging models4.2Kubernetes and service scaling4.3Kubeflow Pipelines4.4Orchestration with Airflow4.5Infrastructure as code with Terraform4.6Cloud platforms: SageMaker, Vertex and Azure ML4.7Secrets and access management4.8Cloud cost control4.9Development, staging and production environments4.10Workshop: deploying a pipeline on Kubernetes
5.1Batch versus real-time inference5.2APIs with FastAPI and model servers5.3Seldon, KServe and BentoML5.4Integration with quoting systems5.5CI/CD for models with GitHub Actions5.6Canary and shadow deployments5.7A/B testing in pricing5.8Latency and availability5.9Rollback and version management5.10Practical: pricing API with canary deployment
6.1Data and concept drift6.2Performance metrics in production6.3Monitoring with Evidently and Prometheus6.4Alerts and observability6.5Automatic retraining6.6Feedback with actual claims experience6.7Model incident management6.8Fairness monitoring6.9Retirement of obsolete models6.10Laboratory: drift detection in a churn model
7.1Regulation (EU) 2024/1689 and high-risk systems7.2EIOPA guidelines on AI governance7.3Model risk and independent validation7.4Documentation: model cards and technical sheets7.5Explainability with SHAP and LIME7.6Auditing and traceability of decisions7.7Model security and adversarial attacks7.8ISO/IEC 42001 standard for AI management7.9DORA and digital operational resilience7.10Case study: governance file for a model
8.1Definition of the insurance use case8.2Design of the target architecture8.3Data pipeline and features8.4Model training and registration8.5Automated deployment8.6Monitoring and alerts8.7Governance documentation8.8Operating cost estimation8.9Report and presentation8.10Final review with the tutor
How you'll learn
100 % online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the enrolment period, which makes it possible to combine study with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is MLflow, Kubeflow, Docker, Kubernetes, Apache Airflow, in free, academic or evaluation versions. Case studies are based on real procedures for deploying a pricing model as a service, monitoring data and performance drift, and continuous integration and deployment pipelines for models. Assessment is continuous by module, plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Describe the lifecycle of predictive models in an insurer.
Design reproducible data pipelines for machine learning.
Manage experiments, versions and model registries.
Package and orchestrate models using containers.
Deploy models into production in batch and real-time modes.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. A university degree is not required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient command of Spanish to follow technical regulatory texts.
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 800 hours spread over 6 to 8 months. That is an average of 10 to 15 hours per week, compatible with full-time work.
You work with MLflow, Kubeflow, Docker, Kubernetes, Apache Airflow. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
An own-brand SEIUM diploma upon passing the continuous assessment and the integrative project. It is in-house training, not an official qualification from the Ministry.
Yes. Modules passed in a Course or Postgraduate Diploma in the same area are recognised towards the higher programme. Check the recognition policy when you enrol.
Related programmes
Diploma in Risk Parametrisation in Renewable Energy
Online postgraduate diploma of 800 hours in risk parametrisation in renewable energy. 8 modules covering risk parametrisation in renewable energy from fundamentals to validation and implementation,…
Diploma in InsurTech Compliance Auditing
Online postgraduate diploma of 800 hours in InsurTech compliance auditing, structured in 8 modules covering fundamentals, regulatory framework, analysis methods, design, systems integration, risk management, validation…
Postgraduate Diploma in Green Taxonomy and Regulatory Reporting
Online 800-hour Postgraduate Diploma in Green Taxonomy and Regulatory Reporting. 8 modules covering Regulation (EU) 2020/852 (Taxonomy), Delegated Regulation (EU) 2021/2178 (Article 8 disclosures) and Workiva.…
More in Insurance, Risk & Actuarial Data
All Insurance, Risk & Actuarial Data programmes → · How to apply · Fees & financing · Scholarships