Large Language Models and Reasoning in Multi-Agent Systems

Fondazione Bruno Kessler; Trento; In loco; EUR 30.000 - 50.000; Tempo pieno

Descrizione del lavoro

The Fondazione Bruno Kessler offers an internship in the Intelligent Digital Agents Research Unit, focusing on enhancing multi-agent reasoning. Interns will engage in cutting-edge research at the intersection of cognitive AI and digital mental health, contributing to innovative projects that support mental health technologies.

Servizi

Support in finding accommodation

Use of internal canteen service

Participation allowance

Competenze

• Master’s degree or enrollment in related fields.
• Fluent in English (minimum level B2).
• Strong interpersonal and teamwork skills.

Mansioni

• Analyze reasoning behaviors of agents across benchmarks.
• Conduct literature review on LLM fine-tuning.
• Design or test modular improvements to expert agents.

Conoscenze

Interpersonal skills

Teamwork

Adaptability

Initiative

Autonomy

Proficiency in Python

Familiarity with LLMs

Generative AI

Prompt-based modeling

Formazione

Master’s degree in Computer Science, Data Science, Artificial Intelligence, Cognitive Sciences, Psychology

Descrizione del lavoro

Social network you want to login/join with:

Large Language Models and Reasoning in Multi-Agent Systems, Science and Technology Hub - Trento

col-narrow-left

Location:

Science and Technology Hub - Trento, Italy

Job Category:

Other

-

EU work permit required:

Yes

col-narrow-right

Job Reference:

235568453

Job Views:

2

Posted:

20.05.2025

Expiry Date:

04.07.2025

col-wide

Job Description:

The Bruno Kessler Foundation (FBK) is a leading research institution based in Trento, Italy. With over 450 researchers distributed across 12 Research Centers, FBK promotes excellence in science and technology across both technical and social domains.

The internship is offered within the Intelligent Digital Agents (IDA) Research Unit of the Digital Health & Wellbeing Center . The unit focuses on developing flexible, ethically grounded technologies and digital assistants to support mental health and prevention.

More information can be found at https://ida.fbk.eu/

Planned activities

The Research Unit is looking for a young recent graduate interested in pursuing an internship experience in Improving Multi-Agent Reasoning via Literature-Guided Fine-Tuning of Expert Agents.

The intern will contribute to the Pool of Experts framework, which simulates psychologically profiled expert agents engaging in cooperative reasoning. While the architecture works in a zero-shot setting, this internship aims to explore if and how fine-tuning or lightweight adaptations can improve individual expert reasoning and overall decision quality.

Main activities include:

• Analyzing reasoning behaviors of agents across benchmarks;
• Conducting a literature review on LLM fine-tuning , particularly in role- or persona-based setups;
• Designing or testing modular improvements to expert agents;
• Exploring efficient adaptation strategies (e.g., LoRA, prompt tuning);
• Implementing experimental improvements within the PoE system.

This internship offers experience at the frontier of cognitive AI, machine learning, and digital mental health technologies.

Requirements

• Possession of, or enrollment in, a Master’s degree in one of the following fields: Computer Science, Data Science, Artificial Intelligence, Cognitive Sciences, Psychology;
• Fluent knowledge of English (minimum level B2);
• Strong interpersonal and teamwork skills;
• Good adaptability, initiative, and autonomy;
• Proficiency in Python;
• Familiarity with LLMs, generative AI, and prompt-based modeling.

Internship information

• Internship start date: secondsemester 2025
• Opportunity reserved for graduates with a Master's degree (for extra-curricular internships, the degree must not have been obtained more than 12 months ago)
• The internship experience will take place at the Povo location
• We offer support in finding accommodation at affiliated facilities, in the case of off-site candidates
• We offer the possibility to use the internal canteen service
• Possible recognition of participation allowance

How to Apply

All interested parties are asked to fill out the online form by clicking on "Apply Online" in the "Internship opportunities" section, attaching the following documents in .pdf format:

• motivational letter

For any details about the internship activity, please contact: Patrizio Bellan – [emailprotected]

For any further information, please contact the Human Resources Department at: [emailprotected]

Application deadline: the notice will be withdrawn when the desired applications are reached.