Postdoc In Machine Learning And Dynamics GENOVA

Postdoc In Machine Learning And Dynamics
Genova
Liguria, GENOVA

Postdoc in machine learning and dynamics

- (2500001B)

- Commitment & contract: Postdoctoral, 1 year_

- Location: Genoa_

**_ Step into a world of endless possibilities, together let's leave something for the future!_

At IIT, we are committed to advancing human-centered Science and Technology to address the most urgent societal challenges of our era.

We foster excellence in both fundamental and applied research, spanning fields such as neuroscience and cognition, humanoid technologies and robotics, artificial intelligence, nanotechnology, and material sciences, offering a truly interdisciplinary scientific experience.

Our approach integrates cutting-edge tools and technology, empowering researchers to push the limits of knowledge and innovation.

With us, your curiosity will know no bounds.

We are dedicated to providing equal employment opportunities and fostering diversity in all its forms, creating an inclusive environment.

We value the unique experiences, knowledge, backgrounds, cultures, and perspectives of our people.

By embracing diversity, we believe science can achieve its fullest potential.

**THE ROLE

You will be working in a multicultural and multi-disciplinary group, where junior and senior scientists collaborate, each with their expertise, to carry out a scientific activity with a shared research goal.

The success of modern machine learning, particularly in large-scale neural architectures, raises fundamental questions about the interplay between model design, data structure, and generalization principles.

Theoretical foundations of machine learning have traditionally relied on the assumption of independent and identically distributed (i. i. d. )

data, typically represented as Euclidean vectors.

However, this framework is no longer sufficient to explain the properties and performance of modern algorithms, such as large language models.

This project aims to investigate the fundamental principles of modern machine learning, with a particular focus on the role of dynamics and compositional structure in shaping learning processes.

A key aspect of this research is the study of learning problems and algorithms that involve temporal evolution.

Dynamical systems—encompassing both discrete

- and continuous-time formulations—offer a unified framework for modeling complex, structured tasks.

A notable case of interest is controlled dynamical systems, where the learning process is intrinsically linked to solving reinforcement learning problems.

This project aims to develop a learning theory for dynamic algorithms, providing principles for designing more efficient solutions to be tested in practical scenarios

**ESSENTIAL** REQUIREMENTS

- A PhD in mathematics, computer science, engineering, physics, and similar disciplines

- Documented experience in machine learning, statistics, optimization, applied analysis (inverse problems), control theory, reinforcement learning

- A strong mathematical and computational background

- A strong publication record

- The ability to properly report, organize and publish research data

- Documented experience in coaching junior scientists

- Good command of spoken and written English

**ADDITIONAL SKILLS

- Experience in both computational and modeling aspects (e. g.

optimization and statistics / inverse problems)

- Ability to work in a challenging and international environment

- Capacity to work autonomously and collaboratively in a highly interdisciplinary environment

- Possess Analytical Reasoning skills and a growth mindset

**COMPENSATION PACKAGE

- Competitive salary package for international standards

- Private health care coverage depending on your role and contract

- Application's deadline: March 11th, 2025_

**Primary Location** GENOVA S. QUIRICO

**Job** Postdoc

**Job Posting** Feb 24, 2025, 5:21:54 AM