Post-Doctoral Position in Multimodal AI-based Perception: Object Detection and Pose Estimation [...]

Organisation/Company Istituto Italiano di Tecnologia Research Field Engineering Mathematics Physics Researcher Profile Recognised Researcher (R2) Application Deadline 31 Jul 2026 - 00:00 (UTC) Country Italy Type of Contract Other Job Status Other 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

Commitment & contract: collaboration contract

Location: Genova (Italy)

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

At the Italian Institute of Technology (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 provide equal employment opportunities and foster 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 join the Artificial Intelligence for Good (AIGO) research unit, coordinated by Prof. Vittorio Murino, a multicultural and multidisciplinary research group in which junior and senior scientists collaborate toward shared scientific objectives, integrating strong theoretical foundations with application-driven research.

AIGO develops advanced Computer Vision, Machine Learning and Deep Learning methodologies for learning from complex, multimodal, and imperfect data. The research emphasizes robust learning under limited, noisy, or biased supervision — including unsupervised, semi-supervised, and self-supervised paradigms — while addressing key challenges such as domain shift, data imbalance, and continual learning. The activity further encompasses generative models, modern multimodal foundation models, and lightweight, computationally efficient AI techniques designed for deployment in resource-constrained environments.

Within this framework, AIGO will lead the development of the computer vision subsystem of the LILO (LIghtweight LOng-Reach Robotic Arm System) project, a joint initiative between the Italian Space Agency (ASI) and the Italian Institute of Technology. Specifically, LILO aims to realize an advanced robotic platform for autonomous satellite in-orbit servicing, supporting inspection, capture, manipulation, life-extension of orbital assets, and active debris removal.

In the context of LILO, the contribution of AIGO will focus on the design and implementation of the Vision System, a core enabling component for autonomous on-orbit operations. In this context, AIGO has to develop robust perception algorithms for object detection and 6-DoF pose estimation of cooperative and non-cooperative space targets, including space objects.

Your research will address the intrinsic challenges of the space environment — such as extreme illumination variability, specular reflections, partial occlusions, and stringent onboard computational constraints — through the development of advanced machine and deep learning models. A multimodal perception framework will be adopted, integrating heterogeneous sensing modalities (e.g., RGB cameras, LiDAR, event-based and thermal sensors) to ensure robustness, accuracy, and repeatability.

Within the research team, your main responsibilities will include:

• Developing and studying computer vision, machine and deep learning-based models for object recognition and pose estimation from multichannel sensory data.
• Investigating object detection and perception approaches that operate under limited supervision and synthetic and/or heterogeneous data conditions (e.g., supervised, semi-supervised, and self-supervised settings).
• Designing synthetic benchmarking environments and sim-to-real strategies for pose estimation of known and unknown objects.
• Optimizing perception models for embedded deployment and hybrid onboard/ground architectures.
• Conducting research on core AIGO topics, both independently and in collaboration with team members.
• Supervising PhD students and contributing to the coordination of research activities.
• Publishing results in leading international journals and conferences.
• Supporting the preparation of national, international, and industrial research proposals.

ESSENTIAL REQUIREMENTS

• PhD in Computer Science, Artificial Intelligence, Machine Learning, Computer Vision, Robotics, Engineering, Physics, Mathematics, or related fields.
• Strong research background in Machine Learning and Computer Vision.
• Demonstrated experience in perception-related tasks (e.g., object detection, pose estimation, visual understanding, or related areas).
• Solid understanding of modern deep learning methodologies, including representation learning and model generalization.
• Knowledge of recent foundation and multimodal models, such as Vision Transformers and diffusion-based architectures, and their adaptation to downstream tasks.
• Experience working with large-scale models and adapting them to domain-specific applications.
• Excellent programming skills and experience with major deep learning frameworks.
• Strong publication record in internationally recognized scientific venues.
• Ability to work both independently and collaboratively in a multidisciplinary research environment.
• Excellent written and spoken English.

ADDITIONAL SKILLS

• Experience with 3D and geometric vision.
• Proven experience in lightweight machine learning and efficient model deployment, such as model compression, model quantization and distillation methods to minimize computational overhead and memory footprint.
• Knowledge or experience with multimodal approaches and topics such as domain adaptation, few/zero-shot learning, self-supervised learning, model debiasing, and continual learning.
• Strong command of modern deep learning approaches, including Graph Neural Networks (GNNs) and Transformers.
• Experience on deploying and fine-tuning foundational DL models, including LLMs and VLMs.
• Hands-on experience deploying models on HPC infrastructures.
• Capacity to work autonomously and collaboratively in a highly interdisciplinary environment.
• Possess Analytical Reasoning skills and a growth mindset.

COMPENSATION PACKAGE

• A yearly gross salary up to 33.500€
• Private health care coverage depending on your role and contract.
• 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.

This open position is financed by the Italian Space Agency (ASI) in the framework of LILO project (LIghtweight LOng-reach robotic arm system for satellite in-orbit) contract n. 2025-25-HH, CUP F33C25000720001.

Please submit your application using the online form and including a detailed CV, university transcripts, cover letter, and contact details of 2 references.