Apply now
Master'sData, AI, Simulation & Analytics Applications open

Master’s in Multimodality Engineering

Online master's programme of 1,900 hours in multimodal AI engineering. 12 modules covering modality fusion and alignment, per-modality representations, transformer architectures, contrastive learning, multimodal language models, multimodal generation, sensor fusion, multimodal RAG, agents and efficient deployment under the AI Act, the GDPR and ISO/IEC 42001, with an assigned technical tutor.

Duration1900 h
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

Represent data from different modalities in shared spaces.

02

Design transformer-based multimodal fusion architectures.

03

Train models with contrastive learning.

04

Adapt multimodal language models to specific tasks.

05

Build multimodal retrieval and RAG systems.

06

Fuse heterogeneous sensors in engineering applications.

07

Assess the risks and regulatory compliance of multimodal systems.

Profile

Who it's for

  • Multimodal AI engineers building systems that combine text, image, audio and video.
  • Machine learning engineers expanding beyond single-modality models.
  • Vision-language engineers adapting foundation models to industrial tasks.
  • Sensor fusion engineers working on perception and diagnostics.
  • Generative AI researchers interested in multimodal generation.
  • RAG systems engineers working with complex technical documentation.
  • Engineering or science graduates looking to enter the technology sector.
Standards & tools

What you'll work with

  • Regulation (EU) 2024/1689 (AI Act)
  • Regulation (EU) 2016/679 (GDPR)
  • ISO/IEC 42001 (AI management systems)
  • ISO/IEC 22989 (AI concepts and terminology)
  • ISO/IEC 23053 (framework for AI systems using machine learning)
  • Directive (EU) 2019/790 (copyright in the Digital Single Market)
  • ISO/IEC 23894 (AI risk management)
  • PyTorch
  • Hugging Face Transformers
  • OpenCLIP
  • LlamaIndex
  • Weaviate
Syllabus

12 modules · 1900 h

  1. 1.1Modalities: text, image, audio, video and sensors
  2. 1.2Heterogeneity, alignment and complementarity
  3. 1.3Joint and coordinated representations
  4. 1.4Early, late and intermediate fusion
  5. 1.5Translation between modalities
  6. 1.6Co-learning and transfer
  7. 1.7Taxonomy of multimodal tasks
  8. 1.8Historical evolution of the models
  9. 1.9Open research challenges
  10. 1.10Case study: analysis of an industrial multimodal system
  1. 2.1Text embeddings and tokenisation
  2. 2.2Image representations with CNNs and ViTs
  3. 2.3Audio representations and spectrograms
  4. 2.4Speech models such as wav2vec and Whisper
  5. 2.5Video representations
  6. 2.6Sensor time series
  7. 2.7Graphs and structured data
  8. 2.8Point clouds and 3D
  9. 2.9Normalisation across modalities
  10. 2.10Lab: extracting embeddings from several modalities
  1. 3.1Attention and self-attention
  2. 3.2Cross-attention between modalities
  3. 3.3Encoders and decoders
  4. 3.4Visual tokens and patches
  5. 3.5Position and time in multimodal sequences
  6. 3.6Mixture of experts
  7. 3.7Model scaling
  8. 3.8Attention efficiency
  9. 3.9Interpreting attention maps
  10. 3.10Practical: image-text cross-attention transformer
  1. 4.1Contrastive learning with CLIP
  2. 4.2The InfoNCE loss function
  3. 4.3Shared embedding spaces
  4. 4.4Zero-shot classification
  5. 4.5Cross-modal image-text retrieval
  6. 4.6Audio-text alignment
  7. 4.7ImageBind and multiple modalities
  8. 4.8Noisy web data
  9. 4.9Biases in pre-training data
  10. 4.10Lab: semantic image search engine with CLIP
  1. 5.1Vision-language model architectures
  2. 5.2Visual adapters and projectors
  3. 5.3Multimodal instruction tuning
  4. 5.4Visual question answering
  5. 5.5Document understanding
  6. 5.6Video understanding
  7. 5.7Conversational speech models
  8. 5.8Hallucinations in multimodal models
  9. 5.9Evaluation with benchmarks
  10. 5.10Workshop: efficient fine-tuning of a vision-language model
  1. 6.1Text-to-image diffusion models
  2. 6.2Controlling generation
  3. 6.3Video generation
  4. 6.4Speech synthesis
  5. 6.5Audio and music generation
  6. 6.6Text-to-3D generation
  7. 6.7Guided image editing
  8. 6.8Generative quality metrics
  9. 6.9Marking synthetic content
  10. 6.10Practical: controlled generation with diffusion
  1. 7.1Vision and LiDAR in perception
  2. 7.2Radar and camera
  3. 7.3Audio and vibration in diagnostics
  4. 7.4Thermal and visible imaging
  5. 7.5Fusion with Bayesian filters
  6. 7.6Fusion with deep networks
  7. 7.7Synchronisation and calibration
  8. 7.8Robustness to sensor failures
  9. 7.9Industrial applications of sensor fusion
  10. 7.10Lab: camera-LiDAR fusion for 3D detection
  1. 8.1Multimodal vector indexes
  2. 8.2Retrieving documents with images
  3. 8.3RAG over technical manuals
  4. 8.4Video search
  5. 8.5Re-ranking multimodal results
  6. 8.6Evaluating retrieval
  7. 8.7Chunking complex documents
  8. 8.8Vector databases
  9. 8.9Latency and cost
  10. 8.10Workshop: RAG assistant over drawings and manuals
  1. 9.1Agents that see and act
  2. 9.2Tool use from models
  3. 9.3Voice interfaces
  4. 9.4Agents for graphical interfaces
  5. 9.5Robotics with vision-language-action models
  6. 9.6Orchestrating specialised models
  7. 9.7Memory and long context
  8. 9.8Agent security
  9. 9.9Agent evaluation
  10. 9.10Practical: multimodal agent for incident inspection
  1. 10.1Fine-tuning with LoRA
  2. 10.2Quantisation of multimodal models
  3. 10.3Distillation of large models
  4. 10.4Edge inference
  5. 10.5Serving large models
  6. 10.6Optimising training data
  7. 10.7Curating multimodal datasets
  8. 10.8Computational cost of training
  9. 10.9MLOps practices for multimodal systems
  10. 10.10Lab: quantising and deploying a vision-language model
  1. 11.1Multimodal evaluation benchmarks
  2. 11.2Human evaluation protocols
  3. 11.3Multimodal bias and fairness
  4. 11.4Safety and harmful content
  5. 11.5Multimodal adversarial attacks
  6. 11.6Privacy in images and voice
  7. 11.7The AI Act and general-purpose models
  8. 11.8Copyright in training data
  9. 11.9Accessibility through multimodal descriptions
  10. 11.10Case study: risk assessment of a multimodal assistant
  1. 12.1Defining the multimodal task
  2. 12.2Data and curation
  3. 12.3Architecture design
  4. 12.4Training or adaptation
  5. 12.5Quantitative evaluation of the system
  6. 12.6Error and bias analysis
  7. 12.7Prototype deployment
  8. 12.8Conclusions and future work
  9. 12.9Master's Thesis report
  10. 12.10Master's Thesis: defence before a panel
Methodology, software & labs

How you'll learn

100% online training 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 the intake, so you can combine the programme with your job.

Each module combines theory, guided reading of the original standard and applied exercises. The working software is PyTorch, Hugging Face Transformers, OpenCLIP, LlamaIndex and Weaviate, in free, academic or evaluation versions. Real procedures are studied: a semantic image and text search engine, a multimodal RAG assistant over technical documentation, and camera-LiDAR fusion for perception. Assessment is continuous by module, plus the final Master's Thesis.

Standards covered: Regulation (EU) 2024/1689 (AI Act), Regulation (EU) 2016/679 (GDPR), ISO/IEC 42001, ISO/IEC 22989, ISO/IEC 23053, Directive (EU) 2019/790 (copyright) and ISO/IEC 23894.

Assigned technical tutor:every module ends with a deliverable that your tutor marks individually.
Standards-based learning:guided reading of the AI Act, the GDPR and ISO/IEC 42001 applied to real cases, not as a theoretical annex.
Industry software:PyTorch, Hugging Face Transformers, OpenCLIP, LlamaIndex and Weaviate, in free, academic or evaluation versions.
Master's Thesis with defence:a multimodal AI system for a real task, from data curation and architecture design to an evaluated, deployed prototype, defended before a panel.
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.

Define the multimodal task
Specify the task and curate the multimodal dataset.
Design the architecture
Choose the fusion strategy and model architecture.
Train or adapt
Train the model or adapt a foundation model with LoRA.
Evaluate and deploy
Evaluate quantitatively, analyse errors and biases, and deploy a prototype.
Master's Thesis
Present the conclusions and future work, defended before a panel.
Career opportunities

Where this takes you

Multimodal AI EngineerMachine Learning EngineerVision-Language EngineerSensor Fusion EngineerGenerative AI ResearcherRAG Systems Engineer
Admissions & scholarships

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.

Apply now Scholarships
FAQ

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 PyTorch, Hugging Face Transformers, OpenCLIP, LlamaIndex and Weaviate, 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 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
Master's8,850 $

Master’s in Optimisation and OR for Engineering

Online master's programme of 1,900 hours in optimisation and operations research for engineering: 12 modules covering linear and integer optimisation, design optimisation, process optimisation, industrial planning…

1900 hOnlineData, AI, Simulation & Analytics
Master's7,730 $

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,…

1900 hOnlineData, AI, Simulation & Analytics
Master's8,850 $

Master’s in Multiphysics Co-Simulation & FMI Engineering

Online master's programme of 1,900 hours in multiphysics co-simulation and FMI engineering. 12 modules covering multiphysics systems, the FMI standard in depth, co-simulation algorithms, SSP system…

1900 hOnlineData, AI, Simulation & Analytics
Master’s in Multimodality EngineeringEnrol
Related programmes

More in Data, AI, Simulation & Analytics

Master’s in Edge AI & TinyML EngineeringView programme →Master’s in Reinforcement Learning, Control and Safe AI EngineeringView programme →Master’s in Optimisation under Uncertainty EngineeringView programme →Master’s in Time Series, Signals and Edge AI EngineeringView programme →Master’s in Digital Twins and Operations Analytics EngineeringView programme →Master’s in Optimisation and OR for EngineeringView 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.