Postgraduate Diploma in Data/Model Traceability and Technical Auditing
Online 800-hour Postgraduate Diploma in Data/Model Traceability and Technical Auditing. 8 modules covering ISO/PAS 8800:2024, ISO/IEC 5259 and DVC. Assigned tutor and open enrolment.
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
Design the data lineage of automated driving models.
Assess dataset quality using recognised standards.
Version data, code and models in a reproducible way.
Implement logging that makes decisions explainable.
Plan technical audits of models and data.
Integrate traceability into automotive engineering processes.
Write audit reports with actionable findings.
Who it's for
- Autonomous driving data engineer who wants to specialise in Data/Model Traceability and Technical Auditing.
- AI technical auditor who wants to specialise in Data/Model Traceability and Technical Auditing.
- MLOps specialist who wants to specialise in Data/Model Traceability and Technical Auditing.
- Data quality manager who wants to specialise in Data/Model Traceability and Technical Auditing.
- Configuration engineer who wants to specialise in Data/Model Traceability and Technical Auditing.
- AI compliance consultant who wants to specialise in Data/Model Traceability and Technical Auditing.
- Engineering or science graduates seeking to join car manufacturers.
What you'll work with
- ISO/PAS 8800:2024
- ISO/IEC 5259
- Reglamento (UE) 2024/1689
- ISO/IEC 42001:2023
- ISO/IEC 25012
- ISO 19011:2018
- Automotive SPICE 4.0
- ASAM OpenLABEL
8 modules · 800 h
1.1Why models require traceability1.2End-to-end data lineage1.3Acquisition metadata: vehicle, sensor and context1.4Unique identifiers for recordings and frames1.5Relationship between requirements, data and models1.6Traceability required by ISO/PAS 88001.7Recording obligations under Regulation (EU) 2024/16891.8Costs and benefits of traceability1.9Data governance maturity models1.10Case study: reconstructing the lineage of a segmentation model
2.1Data quality model of ISO/IEC 250122.2ISO/IEC 5259 series for analytics and AI2.3Completeness and representativeness with respect to the ODD2.4Labelling quality and inter-annotator agreement2.5ASAM OpenLABEL format2.6Training, validation and test splits without leakage2.7Synthetic data and its provenance2.8Privacy, anonymisation and GDPR2.9Data retention and deletion2.10Workshop: quality report for a pedestrian dataset
3.1Version control with Git and DVC3.2Model and artefact registry3.3Immutable dataset snapshots3.4Training reproducibility3.5Management of seeds, environments and containers3.6Software and model bills of materials3.7Hashes and integrity signatures3.8Linking to the vehicle configuration3.9Version retention policies3.10Laboratory: reproducible pipeline with DVC and MLflow
4.1Event data recorders and DSSAD4.2Logging of model inputs and outputs4.3Explainability techniques: saliency and SHAP4.4Scenario-level explanations4.5Incident reconstruction from logs4.6Temporal synchronisation of sensors4.7Secure storage and chain of custody4.8Access to data by authorities4.9Limits of explainability in deep networks4.10Practice: reconstructing a braking event from logs
5.1Types of audit: internal, second-party and third-party5.2Audit principles according to ISO 190115.3Criteria, scope and sampling5.4Objective evidence in AI systems5.5Process audit versus product audit5.6Checklists for models5.7Competences of the technical auditor5.8Findings and classification of nonconformities5.9Audit report5.10Workshop: audit programme for a perception system
6.1Review of the data specification6.2Verification of declared performance metrics6.3Robustness and perturbation testing6.4Bias assessment by subgroup6.5ODD coverage analysis6.6Audit of the annotation process6.7Independent reproduction of results6.8Audit of changes between versions6.9Third-party risks and pre-trained models6.10Case study: auditing a traffic sign detection model
7.1Automotive SPICE and machine learning processes7.2Configuration management according to ISO 26262-87.3Traceability to the safety case7.4Quality gates in continuous integration7.5Change management and impact analysis7.6Evidence for type approval7.7Requirements and test management tools7.8Traceability metrics for management7.9Continuous improvement following audits7.10Practice: requirement-data-model-test matrix
8.1Selection of the study model8.2Data lineage map8.3Versioning and logging plan8.4Design of decision records8.5Technical audit programme8.6Execution of a simulated audit8.7Findings report8.8Corrective action plan8.9Dissertation and presentation8.10Final review with the tutor
How you'll learn
Fully 100 % online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: students progress at their own pace within the intake, which makes it possible to combine the course with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is DVC, MLflow, Git, CVAT, Apache Atlas, in free, academic or evaluation versions. Case studies draw on real procedures: audits of training datasets, independent reproduction of training runs and reconstruction of incidents from logs. Assessment is continuous per module, plus the final integrating project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Design the data lineage of automated driving models.
Assess dataset quality using recognised standards.
Version data, code and models in a reproducible way.
Implement logging that makes decisions explainable.
Plan technical audits of models and data.
Where this takes you
Requirements
- Prior technical training or professional experience in the sector. No university degree is 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 a full-time job.
The course works with DVC, MLflow, Git, CVAT and Apache Atlas. Free, academic or evaluation versions are used, and the tutor indicates the free alternative wherever one exists.
A SEIUM diploma of your own upon passing the continuous assessment and the integrating project. It is in-house training, not an official qualification from the Ministry.
Yes. Modules passed in a course or diploma in the same area can be credited towards the advanced programme. Check the recognition policy when you enrol.
Related programmes
Postgraduate Diploma in Risk-Based Scenario Catalogues and ODD KPIs
Online 800-hour Postgraduate Diploma in Risk-Based Scenario Catalogues and ODD KPIs. 8 modules covering ISO 34502:2022, ISO 34503:2023 and esmini. Assigned tutor and open enrolment.
Postgraduate Diploma in RTOS, Hypervisors and Mixed-Criticality
Online 800 h Postgraduate Diploma in RTOS, Hypervisors and Mixed-Criticality. 8 modules covering ISO 26262:2018, ISO/SAE 21434:2021 and QNX Neutrino RTOS. Assigned tutor and open enrolment.
Postgraduate Diploma in Edge Analytics for Predictive Maintenance
Online 800-hour Postgraduate Diploma in Edge Analytics for Predictive Maintenance. 8 modules with ISO 13374-1, ISO 17359:2018 and Eclipse Kuksa. Assigned tutor and open enrolment.
More in Autonomous, ADAS & Software-Defined Vehicle
All Autonomous, ADAS & Software-Defined Vehicle programmes → · How to apply · Fees & financing · Scholarships