Research Title:
Safe-by-Design Deep Learning: From Uncertainty Quantification to Large Language Models
Funded by:
The Italian Institute of Artificial Intelligence (AI4I), in collaboration with Politecnico di Torino
Supervisors:
Luca Laurenti, Eliana Pastor
Contact:
luca.laurenti@ai4i.it
The Italian Institute of Artificial Intelligence (AI4I), in collaboration with Politecnico di Torino, invites applications for a PhD position focused on developing safe-by-design deep learning models that provide quantifiable guarantees of robustness and reliability.
The goal of this PhD project is to develop techniques to quantify the robustness of deep learning models and to use these techniques to design state-of-the-art deep learning models that not only are accurate, but also come with quantifiable correctness guarantees. To achieve this, the PhD will explore and devise techniques at the intersection of machine learning, probability theory, control theory, and formal methods.
The Role
The selected PhD candidate will work at the intersection of machine learning, probability theory, control theory, and formal methods, developing methods that enable deep learning systems to make safe and reliable predictions under uncertainty. The research will be carried out jointly between AI4I and Politecnico di Torino, with additional collaboration from TU Delft.
Key Objectives
- Develop methods for uncertainty quantification and robustness analysis in deep learning.
- Design safe-by-design neural architectures that incorporate probabilistic safety guarantees during training.
RESEARCH PLAN
Year 1 – Uncertainty Quantification and Robustness Analysis
Study existing methods such as randomized smoothing and Bayesian neural networks to quantify uncertainty in model predictions.
Evaluate how these techniques can measure and improve the safety of modern deep learning architectures.
Year 2 – Safe-by-Design Model Development
Design novel learning algorithms and architectures that integrate uncertainty-based constraints directly into training.
Experiment with benchmark datasets and tasks to assess performance and robustness.
Year 3 – Applications to Large-Scale and Industrial Systems
Apply safe-by-design techniques to large language models and cutting-edge architectures.
Explore potential industrial collaborations to evaluate methods in real-world scenarios.
Expected Impact and Dissemination
The project will contribute to developing trustworthy AI systems with measurable safety guarantees.
Results will be published in top-tier conferences and journals such as:
- Machine Learning and AI: NeurIPS, ICML, ICLR, UAI, AISTATS, IJCAI, AAAI
- Journals: IEEE TKDE, ACM TKDD, ACM TIST
Required Qualifications
- Strong background in machine learning, deep learning, or applied mathematics.
- Good programming skills and proficiency in one or more programming languages
- Strong analytical skills and the ability to work across multiple research domains.
- Fluency in English (written and spoken).
What We Offer
- Joint supervision between AI4I and Politecnico di Torino, fostering academic collaboration.
- Opportunity to contribute to open-source research, publications, and community datasets.
- Access to high-performance computing infrastructure and expert network.
- A collaborative, international research environment with exposure to both academic and industry partners.
Start Date:
01/03/2026
How to Apply
Applications for this position are managed by Politecnico di Torino.
Please apply via the university’s official PhD portal:
For More Information
ABOUT US
AI4I – THE ITALIAN RESEARCH INSTITUTE FOR ARTIFICIAL INTELLIGENCE FOR INDUSTRIAL IMPACT
AI4I has been founded to perform transformative, application-oriented research in Artificial Intelligence.
AI4I is set to engage and empower gifted, entrepreneurial, young researchers who commit to producing an impact at the intersection of science, innovation, and industrial transformation.
Highly competitive pay, bonus incentives, access to dedicated high-performance computing, state-of-the-art laboratories, industrial collaborations, and an ecosystem tailored to support the initiation and growth of startups stand out as some of the distinctive features of AI4I, bringing together people in a dynamic international environment.
AI4I is an Institute that aims to enhance scientific research, technological transfer, and, more generally, the innovation capacity of the Country, promoting its positive impact on industry, services, and public administration. To this end, the Institute contributes to creating a research and innovation infrastructure that employs artificial intelligence methods, with particular reference to manufacturing processes, within the framework of the Industry 4.0 process and its entire value chain. The Institute establishes relationships with similar entities and organizations in Italy and abroad, including Competence Centers and European Digital Innovation Hubs (EDIHs), so that the center may become an attractive place for researchers, companies, and start-ups.
