Istituto Italiano di Tecnologia

One Postdoctoral position on multimodal and generative AI models for scene understanding

Italy

Commitment & contract: collaboration contract, 12 months (renewable)

Location: Genova, via Enrico Melen 83

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 shared research goals. 

The Artificial Intelligence for Good (AIGO) Research Unit is coordinated by Prof. Vittorio Murino. It focuses on fundamental AI topics from methodological and theoretical perspectives, yet functional to tackle a number of applications and actual case studies related to several domains such as biomedical, healthcare, and several others ultimately leading to people wellbeing.

Specifically, AIGO aims at studying learning paradigms in presence of imperfect data, especially in multimodal scenarios, hence tackling unsupervised, semi-supervised and self-supervised settings, weakly or noisy labeled data, few, class imbalanced, or biased. Domain adaptation and generalizationfew/zero-shot learninglearning with biased data, and continual learning, even extended to multimodal scenarios, are among the major areas to be investigated, also given their valence in tackling practical, real-world applications.

AIGO will also consider generative AI models, especially related to the most recent trend regarding multimodal foundation models, including large language models (LLMs) and vision and language models (VLMs). From a general standpoint, AIGO will also consider architectural and computational issues addressing the so-called lightweight Machine Learning in order to design low-power ML technologies and approaches dealing with machine intelligence at the very edge of the cloud (e.g., for robots). Given the focus on people wellbeing, we clearly aim at the design of AI methods considering at their ground ethicalprivacy and fairness aspects, as well as their robustness, towards the design of explainable, trustworthy and transparent deep learning techniques.

Main applications will involve biomedical, biological, neuroscience, and healthcare in general. Brain investigation (and its diseases) is identified as the main (but not exclusive) area of interest. Ultimately, AIGO will seek to develop models that can also be readily applicable to IIT interdisciplinary research, ranging from neuroscience to robotics, in particular by leveraging our in-house robotics platforms (iCub, ErgoCub, R1 et al.), IIT neuroscience teams, and HPC computational facilities.

AIGO benefits from the collaboration with several universities and research centers worldwide, most often with the closer universities of Genova and Verona. AIGO is part of ELLIS (https://ellis.eu/) – an European network of excellence in AI, Machine Learning (ML) and Computer Vision (CV), of which Prof. Murino is a Fellow member.

Within the research team, your main responsibilities will be:

  • Pursue of research in some of the above-mentioned topics addressed by AIGO Research Line, at both individual and collaborative level. Interdisciplinarity research along IIT Flagship programs is also an important aspect in AIGO and in IIT in general;
  • Supervision of the research activities of PhD students;
  • Publications on major conferences and top journals;
  • Search and preparation of funding opportunities, e.g., project proposals to apply to national and international grants, as well as to acquire funds from industrial partners.

ESSENTIAL REQUIREMENTS

  • A PhD in Computer Science, Machine Learning, Computer Vision, Physics, Engineering, Mathematics or related areas;
  • Documented expertise in:
  • Computer Vision, with focus on multimodal learning;
  • Deep generative models, e.g., GANs, diffusion models, encoder-decoder architectures, or optimal transport models;
  • ML and CV approaches with a preference for former and recent deep learning models (GNNs, Transformers, etc.).
  • Strong programming ability (Python preferred) with hands-on skills in AI and Deep Learning frameworks (e.g., Pytorch, Tensorflow or equivalent tools);
  • Spouse the mainstream AIGO research line above quoted;
  • Ability/willingness to integrate within multidisciplinary research group;
  • Proven strong track publications record in the relevant technical areas;
  • Ability to properly report, organize and publish research data;
  • High motivation to learn;
  • Good priority management;
  • Fluency in spoken and written English.

ADDITIONAL SKILLS

  • Knowledge/experience on multimodal approaches, and possibly on (some of) the topics above quoted (e.g., domain adaptation, few-shot learning, self-supervised learning, model debiasing, etc.);
  • Experience with deep learning approaches applied to different science domains, such as chemistry, materials, physics, imaging, drug discovery, climate/weather forecast, etc.;
  • Knowledge of 3D vision (multi-view geometry, point cloud data processing, neural rendering, Gaussian splatting, etc.);
  • Knowledge of graph neural networks;
  • Experience in deploying and fine-tuning DL models, also large language or vision-language models;
  • Practical experience on deploying ML models on HPC platforms;
  • Team player skills with the ability to communicate technical knowledge in a clear and understandable manner;
  • Capacity to work autonomously and collaboratively in a challenging highly interdisciplinary environment;
  • Possess analytical reasoning skills and a growth mindset.

COMPENSATION PACKAGE

  • A yearly gross salary ranging between 32k€ and 40k€;
  • Private health care coverage;
  • Candidates from abroad or Italian citizens who have carried scientific research activity permanently abroad and meet specific requirements, may be entitled to a deduction from taxable income of up to 90% from 6 to 13 years.

Please submit your application using the online form and including:

  • A detailed CV with a full list of publications. Evidence of “Relevant skills” commenting on the strong points where your CV matches the required skills (listed above) will be appreciated.
  • Contact details of 2 references.

Application’s deadline: May 15th, 2025

To discover more about life at IIT, visit the dedicated section here: https://www.iit.it/en/work-at-iit

Apply now

Fill in the form below and send your application.

By marking the checkbox, you accept our privacy policy
You must accept the treatment of personal data