Post-Doctoral Research Visit F/M Developing Lightweight Neural Network Architectures for Enhanced AI in Hospital Settings

Contract type : Fixed-term contract

Renewable contract : Yes

Level of qualifications required : PhD or equivalent

Fonction : Post-Doctoral Research Visit

About the research centre or Inria department

The Inria centre at Université Côte d'Azur includes 42 research teams and 9 support services. The centre's staff (about 500 people) is made up of scientists of diﬀerent nationalities, engineers, technicians and administrative staff. The teams are mainly located on the university campuses of Sophia Antipolis and Nice as well as Montpellier, in close collaboration with research and higher education laboratories and establishments (Université Côte d'Azur, CNRS, INRAE, INSERM ...), but also with the regiona economic players.

With a presence in the fields of computational neuroscience and biology, data science and modeling, software engineering and certification, as well as collaborative robotics, the Inria Centre at Université Côte d'Azur is a major player in terms of scientific excellence through its results and collaborations at both European and international levels.

Context

The project aims to create novel lightweight neural network architectures specifically designed to improve the use of artificial intelligence (AI) in critical healthcare settings, such as hospitals. The ultimate goal is to enhance medical imaging and analysis capabilities, as well as adapt AI models to diverse data types like text and biological data.

By collaborating with the Centre Antoine Lacassagne of Nice, we will gain access to clinical expertise and a wealth of heterogeneous data, facilitating the development of more accurate and robust AI solutions. The project's focus on image segmentation and domain adaptation will enable the integration of full body PET/CT imaging data with healthcare records and biological information.

Assignment

Our approach will involve designing and implementing lightweight neural network architectures that can efficiently process complex medical data while maintaining computational efficiency. We will draw upon a range of techniques, including transfer learning, knowledge distillation, and neural cellular automata, to create models that are not only effective but also scalable and interpretable.

Our development process will prioritize the production of high-quality analysis outputs, ensuring that our findings are actionable and provide tangible value to healthcare professionals. We will maintain an iterative approach, refining our models and techniques as needed to address emerging challenges and refine our results.

Main activities

Conduct research and development of novel lightweight neural network architectures for medical image analysis, such as image segmentation, object detection, and image classification
Develop and optimize algorithms for medical image processing, including image denoising, image enhancement, and image registration, using lightweight neural networks
Collaborate with clinicians and radiologists to collect and annotate large datasets of medical images, and to validate the performance of developed models in real-world hospital settings
Implement and test models on various hardware platforms, including GPUs, CPUs, and specialized AI accelerators, to ensure efficient deployment in hospital settings
Develop and maintain software tools and libraries for medical image analysis, including data preprocessing, model training, and model evaluation
Publish research findings in top-tier conferences and journals, and present results at international conferences and workshops
Participate in the development of grant proposals and research funding applications to support ongoing research activities
Supervise and mentor graduate students and junior researchers in the development of their research projects and skills

Skills

Strong background in statistical and deep learning
Experience with medical image analysis, including image segmentation, object detection, and image classification
Proficiency in programming languages such as Python
Familiarity with deep learning frameworks such as TensorFlow, PyTorch, and Keras
Experience with medical imaging software and libraries, including ITK, 3D Slicer, and scikit-image
Knowledge of image processing techniques, including image denoising, image enhancement, and image registration
Understanding of computer vision and machine learning concepts, including feature extraction, object recognition, and pattern classification
Experience with model optimization techniques, including pruning, quantization, and knowledge distillation
Familiarity with hardware platforms, including GPUs, CPUs, and specialized AI accelerators
Strong understanding of data structures and algorithms, including data preprocessing, model training, and model evaluation
Strong analytical and problem-solving skills, including the ability to design and implement experiments, and to analyze and interpret results
Excellent communication and collaboration skills, including the ability to work with clinicians, radiologists, and other researchers
Experience with version control systems, including Git and GitHub
Experience with writing and publishing research papers, including the ability to prepare and submit manuscripts to top-tier conferences and journals.

Benefits package

Subsidized meals
Partial reimbursement of public transport costs
Leave: 7 weeks of annual leave + 10 extra days off due to RTT (statutory reduction in working hours) + possibility of exceptional leave (sick children, moving home, etc.)
Possibility of teleworking (after 6 months of employment) and flexible organization of working hours
Professional equipment available (videoconferencing, loan of computer equipment, etc.)
Social, cultural and sports events and activities
Access to vocational training
Social security coverage

Remuneration

Gross Salary: 2788 € per month

Apply for this position

General Information

Theme/Domain : Computational Neuroscience and Medicine
Biologie et santé, Sciences de la vie et de la terre (BAP A)
Town/city : Sophia Antipolis
Inria Center : Centre Inria d'Université Côte d'Azur
Starting date : 2025-07-01
Duration of contract : 1 year, 10 months
Deadline to apply : 2025-06-13

Warning : you must enter your e-mail address in order to save your application to Inria. Applications must be submitted online on the Inria website. Processing of applications sent from other channels is not guaranteed.

Instruction to apply

Defence Security :
This position is likely to be situated in a restricted area (ZRR), as defined in Decree No. 2011-1425 relating to the protection of national scientific and technical potential (PPST).Authorisation to enter an area is granted by the director of the unit, following a favourable Ministerial decision, as defined in the decree of 3 July 2012 relating to the PPST. An unfavourable Ministerial decision in respect of a position situated in a ZRR would result in the cancellation of the appointment.

Recruitment Policy :
As part of its diversity policy, all Inria positions are accessible to people with disabilities.

Contacts

Inria Team : EPIONE
Recruiter :
Lorenzi Marco / Marco.Lorenzi@inria.fr

The keys to success

The ideal candidate for this project would possess a strong background in computer science, electrical engineering, or a related field, with a focus on machine and statistical learning. A Ph.D. in one of these fields, combined with experience in medical image analysis, including image segmentation, object detection, and image classification, would be highly desirable.

A strong analytical and problem-solving mindset would be crucial for this role, including the ability to design and implement experiments, and to analyze and interpret results. Excellent communication and collaboration skills would also be necessary, as the collaborator would need to work closely with cross-functional teams, including clinicians and radiologists, to collect and annotate large datasets of medical images.

About Inria

Inria is the French national research institute dedicated to digital science and technology. It employs 2,600 people. Its 200 agile project teams, generally run jointly with academic partners, include more than 3,500 scientists and engineers working to meet the challenges of digital technology, often at the interface with other disciplines. The Institute also employs numerous talents in over forty different professions. 900 research support staff contribute to the preparation and development of scientific and entrepreneurial projects that have a worldwide impact.