Apply now
Postgraduate DiplomaData, AI, Simulation & Analytics Applications open

Diploma in Mixed Pipelines Simulation-High Performance AI

Online postgraduate diploma of 800 hours in high-performance mixed simulation-AI pipelines. 8 modules covering simulation-AI integration, large-scale data generation, high-performance surrogate models, online coupling, scientific MLOps, accelerated design optimisation and pipeline performance, cost and quality, with an assigned technical tutor.

Duration800 hours · 6–8 months
ModeOnline
LanguageEnglish
Start datesSet by the faculty
AwardSEIUM Institute diploma
Enrol now View syllabus Ask an advisor
Virtual lab · try it before you enrol

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.

SIM · LIVE ●
Learning outcomes

What you will be able to do

01

Design architectures that integrate numerical simulation and artificial intelligence.

02

Automate large-scale generation of simulation data.

03

Train surrogate models and neural operators at scale.

04

Couple AI models online with running solvers.

05

Orchestrate pipelines with scientific MLOps tools.

06

Accelerate optimisation processes with surrogates and active learning.

07

Evaluate the performance, cost and quality of pipelines.

Profile

Who it's for

  • Scientific machine learning engineers building surrogates on physical data.
  • HPC engineers who want to bring AI workloads onto their clusters.
  • CAE simulation engineers looking to accelerate their studies with AI.
  • MLOps engineers moving into scientific and engineering pipelines.
  • AI-for-science researchers who need production-grade pipelines.
  • Architects of scientific data platforms.
  • Engineering or science graduates seeking to enter the aerospace sector.
Standards & tools

What you'll work with

  • FMI 3.0 (Functional Mock-up Interface) (standard for exchanging and co-simulating dynamic models)
  • ISO/IEC 23053:2022 (framework for AI systems using machine learning)
  • ISO/IEC 5338:2023 (AI system life cycle processes)
  • MPI 4.0 (message-passing interface for parallel computing)
  • ONNX (Open Neural Network Exchange) (open format for exchanging neural network models)
  • ISO/IEC 25012:2008 (data quality model)
  • OCI Image Format Specification (open container image format)
  • NVIDIA PhysicsNeMo
  • PyTorch
  • Ray
  • SmartSim
  • OpenFOAM
Syllabus

8 modules

  1. 1.1Surrogate, PINN and operator paradigms
  2. 1.2Simulation as a data generator
  3. 1.3AI in the simulation loop
  4. 1.4Performance requirements of mixed pipelines
  5. 1.5HDF5 and netCDF scientific data formats
  6. 1.6Data size and storage
  7. 1.7Examples in CFD, structures and climate
  8. 1.8Reproducibility challenges
  9. 1.9Reference architecture
  10. 1.10Workshop: designing a simulation-training pipeline
  1. 2.1Design of experiments for training
  2. 2.2Parameter sweeps on HPC
  3. 2.3Automating meshing and pre-processing
  4. 2.4Batch solver execution
  5. 2.5Field extraction and post-processing
  6. 2.6Data compression with controlled loss
  7. 2.7Labelling and metadata
  8. 2.8Quality control of simulations
  9. 2.9Cost per generated sample
  10. 2.10Lab: generating a CFD dataset with OpenFOAM
  1. 3.1Convolutional networks on fields
  2. 3.2Graph networks for meshes
  3. 3.3FNO and DeepONet neural operators
  4. 3.4Physics-informed neural networks
  5. 3.5Reduced-order models with autoencoders
  6. 3.6Distributed training with PyTorch DDP
  7. 3.7Mixed precision and Tensor Cores
  8. 3.8Error evaluation against the solver
  9. 3.9Surrogate uncertainty
  10. 3.10Lab: Fourier neural operator with NVIDIA PhysicsNeMo
  1. 4.1Online training with a running simulation
  2. 4.2SmartSim and SmartRedis libraries
  3. 4.3In-memory transfer between processes
  4. 4.4Inference inside the solver
  5. 4.5C++, Fortran and Python interoperability
  6. 4.6Exporting models to ONNX and TorchScript
  7. 4.7Coupling latency and throughput
  8. 4.8Accelerated simulations with AI corrections
  9. 4.9Managing shared GPUs
  10. 4.10Practical exercise: model inference inside a solver
  1. 5.1Workflows with Ray and Dask
  2. 5.2Kubeflow and pipelines on Kubernetes
  3. 5.3Experiment tracking with MLflow
  4. 5.4Data and model versioning
  5. 5.5Managing large artefacts
  6. 5.6Joint scheduling on HPC and cloud
  7. 5.7Caching and reuse of results
  8. 5.8Fault tolerance
  9. 5.9Pipeline observability
  10. 5.10Lab: training pipeline with Ray
  1. 6.1Bayesian optimisation with surrogates
  2. 6.2Active learning to select simulations
  3. 6.3Multi-objective optimisation with surrogates
  4. 6.4Inverse design with differentiable models
  5. 6.5Multi-fidelity simulation and bias correction
  6. 6.6Accelerated uncertainty quantification
  7. 6.7Design space exploration
  8. 6.8Stopping criteria and budget
  9. 6.9Verifying the final design with the solver
  10. 6.10Case study: surrogate-assisted aerodynamic optimisation
  1. 7.1End-to-end pipeline profiling
  2. 7.2Balancing generation and training
  3. 7.3Energy consumption and efficiency
  4. 7.4Cost per trained model
  5. 7.5Accuracy regression testing
  6. 7.6Scientific data governance
  7. 7.7Data and model security
  8. 7.8Documentation and reproducibility
  9. 7.9Scaling to industrial production
  10. 7.10Case study: performance audit of an existing pipeline
  1. 8.1Definition of the physical problem
  2. 8.2Data generation plan
  3. 8.3Automated simulation pipeline
  4. 8.4Training the surrogate model
  5. 8.5Online or batch coupling
  6. 8.6Orchestration and tracking
  7. 8.7Accuracy and performance evaluation
  8. 8.8Cost and scalability analysis
  9. 8.9Report and presentation
  10. 8.10Final project: final review with the tutor
Methodology, software & labs

How you'll learn

Training is 100% online on the SEIUM campus, with downloadable material, 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 alongside your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is NVIDIA PhysicsNeMo, PyTorch, Ray, SmartSim and OpenFOAM, in free, academic or evaluation versions. Case studies are based on real procedures: generating simulation datasets on clusters, training surrogate models on physical fields and design optimisation with active learning. Assessment is continuous by module, plus the final integrating project.

Standards covered: FMI 3.0 (Functional Mock-up Interface), ISO/IEC 23053:2022, ISO/IEC 5338:2023, MPI 4.0, ONNX (Open Neural Network Exchange), ISO/IEC 25012:2008, OCI Image Format Specification

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of FMI 3.0, ISO/IEC 23053 and ISO/IEC 5338 applied to real cases, not as a theoretical annex.
Industry software:NVIDIA PhysicsNeMo, PyTorch, Ray, SmartSim and OpenFOAM, in free, academic or evaluation versions.
Final project:a complete simulation-AI pipeline for a real physical problem, from data generation and surrogate training to coupling, orchestration and cost analysis, reviewed by your tutor.
Flexible format:100% online, no fixed timetables, compatible with full-time work.
Capstone project

Build it end to end

Your final project follows the real engineering workflow, step by step, reviewed by your tutor.

Physical problem and data plan
Define the physical problem and plan the generation of training data.
Automated simulation pipeline
Build an automated simulation pipeline that produces a quality-controlled dataset.
Surrogate model training
Train a surrogate model and evaluate its error against the solver.
Coupling and orchestration
Couple the model online or in batch and orchestrate the pipeline with tracking.
Final project
Accuracy, performance, cost and scalability analysis, written up in a report and presentation reviewed by your tutor.
Career opportunities

Where this takes you

Scientific machine learning engineerHPC engineerCAE simulation engineerMLOps engineerAI-for-science researcherScientific data platform architect
Admissions & scholarships

Requirements

  • Prior technical training or professional experience in the sector. A university degree is not required.
  • An 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.

Apply now Scholarships
FAQ

Frequently asked questions

The programme totals 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.

You work with NVIDIA PhysicsNeMo, PyTorch, Ray, SmartSim and OpenFOAM, 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 final project. 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 are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.

Prior technical training or professional experience in the sector (no university degree required), a computer able to run the programme 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.

Keep exploring

Related programmes

See all in Data, AI, Simulation & Analytics
Postgraduate Diploma1,670 $

Diploma in Industrial Photogrammetry and Point Clouds

Online postgraduate diploma of 800 hours in industrial photogrammetry and point clouds. 8 modules covering photogrammetry and projective geometry, camera calibration, target-based measurement and bundle adjustment,…

800 hours · 6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma2,000 $

Diploma in Time Series Models for Engineering (ARIMA→DL)

Online postgraduate diploma of 800 hours in time series models for engineering, from ARIMA to deep learning. 8 modules covering ARIMA and state-space models, machine learning…

800 hours · 6–8 monthsOnlineData, AI, Simulation & Analytics
Postgraduate Diploma1,670 $

Diploma in Graph Analytics Pipeline Production

Online postgraduate diploma of 800 hours in production graph analytics pipelines, with 8 modules covering graph platform architecture, ingestion and graph construction, graph analytics algorithms, orchestration…

6–8 monthsOnlineData, AI, Simulation & Analytics
Diploma in Mixed Pipelines Simulation-High Performance AIEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Diploma in V&V of Critical Models and Safety CasesView programme →Diploma in PdM Deployment: Integration with SCADA/CMMSView programme →Diploma in Experiment Management and Model-Real CorrelationView programme →Diploma in Graph Analytics Pipeline ProductionView programme →Diploma in Roadmap, Data SLAs and Service ContractsView programme →Diploma in Scenarios, Trade-offs and Sensitivity AnalysisView programme →

All Data, AI, Simulation & Analytics programmes → · How to apply · Fees & financing · Scholarships

Scroll to Top
SEIUM – Institute of Advanced Engineering
Powered by  GDPR Cookie Compliance
Privacy Overview

This website uses cookies so that we can provide you with the best user experience possible. Cookie information is stored in your browser and performs functions such as recognising you when you return to our website and helping our team to understand which sections of the website you find most interesting and useful.