IdR72/26 - Reinforcement Learning Methods and Software Frameworks for the Intelligent Control of Hybrid Building Energy Systems

Italian Ministry of Education, University and Research; Italia; On-site; EUR 32,000 - 52,000; Full time

Job summary

The University of Verona invites applications for a research position in Engineering, focusing on developing and validating reinforcement learning methods for the adaptive and multi-objective control of hybrid building energy systems. The project will develop an RL-based supervisory framework and use realistic simulations and data for offline training, sim-to-real transfer, and safe online adaptation.

Eligibility requires a Master’s Degree in Artificial Intelligence (within six years), a

Qualifications

• Master’s Degree in Artificial Intelligence obtained no more than six years before the expiry date.
• Possession of a curriculum suitable for assisting in carrying out research activities.
• Knowledge of the English language.

Education

Master’s Degree in Artificial Intelligence

Job description

Organisation/Company Università degli Studi di Verona Research Field Engineering Researcher Profile Recognised Researcher (R2) Leading Researcher (R4) First Stage Researcher (R1) Established Researcher (R3) Application Deadline 29 Oct 2026 - 13:00 (UTC) Country Italy Type of Contract To be defined Job Status Not Applicable Is the job funded through the EU Research Framework Programme? Not funded by a EU programme Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The research aims to develop and validate innovative Reinforcement Learning (RL) methods for the adaptive and multi-objective control of hybrid building energy systems combining multi-source heat pumps, conventional heating systems, boilers, thermal storage, and renewable energy sources. The research will contribute to the development of a prototype RL-based supervisory control framework operating as a non-invasive intelligence layer on existing HVAC systems and exploiting realistic simulation environments and operational data for offline training, safe policy improvement, sim-to-real transfer, and controlled online adaptation. Particular attention will be devoted to safety, robustness, and explainability. The developed methodologies will be evaluated using realistic simulations and, where feasible, real operational scenarios, assessing their impact on energy consumption, operating costs, CO₂ emissions, and indoor comfort

For admission to the selection process referred to in Art. 1, potential candidates must fulfil the following requirements:
a) Master’s Degree in Artificial Intelligence [Laurea Magistrale o a ciclo unico awarded pursuant to Art. 3(1n), Ministerial Decree no. 270 of 22/10/04], obtained no more than six years before the expiry date of this call;
b) Possession of a curriculum suitable for assisting in carrying out research activities;
c) Knowledge of the following foreign language: English.

• Italy

Eligibility of fellows: country/ies of residence:

• AFRICA
• EUROPE
• OCEANIA
• NORTH AMERICA
• SOUTH AMERICA
• ASIA

Eligibility of fellows: nationality/ies:

• AFRICA
• EUROPE
• OCEANIA
• NORTH AMERICA
• SOUTH AMERICA
• ASIA

Selection process

The competition will be carried out by an evaluation of titles and examination by means of an interview.