PhD in Safe Control via Generative AI

Research Title:

Safe Control via Generative AI

Deadline:

25 May 2026

Funded by:

The Italian Institute of Artificial Intelligence (AI4I), in collaboration with IMT

Supervisors:

Luca Laurenti

Contact:

[email protected]

The Italian Institute of Artificial Intelligence (AI4I), in collaboration with IMT, invites applications for a PhD position focused on Safe control via Generative AI.

Modern deep learning models have achieved state-of-the-art performance across various domains, including computer vision and natural language processing. They also hold great promise for controlling and verifying dynamical systems. However, modern machine learning models commonly lack safety and performance guarantees. Consequently, how to utilise these techniques to control autonomous systems with safety and performance guarantees remains an open question. The goal of this PhD project is to determine how to answer this question

The Role

The PhD candidate will explore how state-of-the-art machine learning and generative AI techniques can be used to control dynamical systems while providing performance and safety guarantees. The goal of this PhD project will be to develop a novel control framework that relies on recent developments in machine learning and generative AI and combines them with existing control techniques, such as model predictive control, planning algorithms, or abstractions. Depending on the candidate's interests, the project will involve developing new algorithms at the intersection of machine learning, robotics, and control theory.

The research program will be conducted in collaboration with the Italian Institute of Artificial Intelligence for Industry (AI4I), the Delft Institute of Technology (TU Delft), and the University of Colorado Boulder (CU Boulder).

Key Objectives

* Develop a novel control framework combining generative AI and existing control techniques.

* Explore applications at the intersection of machine learning, robotics, and control theory.

Expected Impact and Dissemination

Scientific results are expected to be published in leading conferences and journals, such as:

* Conferences: NeurIPS, ICML, ICLR, CDC, UAI, AISTATS, IJCAI, AAAI

* Journals: IEEE Transactions on Automatic Control (TAC), Automatica

The project will contribute to safe and reliable AI-driven control methods for modern autonomous systems.

Required Qualifications

* Strong background in machine learning, deep learning, or applied mathematics.

* Good programming skills and proficiency in one or more programming languages (e.g., Python, MATLAB, C++).

* Strong analytical skills and ability to work across multiple research domains.

* Fluency in English (written and oral).

What We Offer

* Joint supervision by AI4I and IMT, with collaboration from TU Delft and CU Boulder.

* Access to AI4I’s high-performance computing resources and research ecosystem.

* Opportunities for international collaboration and high-impact publications.

* A dynamic, interdisciplinary research environment bridging machine learning, generative AI, and control theory.

Start Date:

1 November 2026

How to Apply

Applications for this position are managed by IMT University.

Please submit your application through the official PhD admissions portal.

For additional information, please refer to the following resources:

Call for Applications (Italian):

https://www.imtlucca.it/sites/default/files/2026-03/Bando%20per%20albo.pdf

Executive summary in English:

https://www.imtlucca.it/sites/default/files/2026-03/PhD%20call%20for%20applications_SyS%20XLII.pdf

Application form:

https://pica.cineca.it/imtlucca/imtlucca-phd-sys-2026/

About Us

The Italian Institute for Artificial Intelligence (AI4I) was founded as a research institute to perform transformative, application-oriented research in Artificial Intelligence, driving innovation and industrial progress. The Institute is designed to engage and empower gifted, entrepreneurial, and ambitious researchers who are committed to generating real-world impact at the intersection of science, technology, and industrial transformation.

Competitive salaries, performance-based incentives, access to dedicated high-performance computing resources, state-of-the-art laboratories, and strong industrial collaborations are among the distinctive features that define AI4I. The Institute fosters a dynamic international environment and an ecosystem that supports the creation and growth of innovative startups.

AI4I’s mission is to advance scientific research, technology transfer, and, more broadly, Italy’s innovation capacity, promoting positive impact across industry, services, and public administration. To achieve this, the Institute contributes to building a research and innovation infrastructure that leverages AI methods, with a special focus on manufacturing processes and the broader Industry 4.0 value chain.

AI4I also maintains strategic relationships with leading organizations in Italy and abroad, including Competence Centers and European Digital Innovation Hubs (EDIHs), positioning itself as an attractive destination for researchers, companies, and startups seeking collaboration and impact.