Post-doctoral fellow (M/F) for tin Self-Supervised Learning for 3D Super-Resolution Fluorescenc[...]

CNRS; France; Sur place; EUR 36 000 - 45 000; Plein temps

Résumé du poste

A research organization is looking for a First Stage Researcher to join their NanoBio team in France. The role involves developing novel machine learning models for fluorescence microscopy applications. Candidates should have strong expertise in machine learning, particularly self-supervised learning, and experience with Python programming. This full-time position offers an interdisciplinary environment and the possibility of contract extension.

Qualifications

• Previous experience in machine learning, particularly in self-supervised learning.
• Knowledge of unlabeled data problems, pretext tasks, and related approaches.
• Strong communication skills for teamwork and interdisciplinarity.

Responsabilités

• Assessing theoretical performance of the system through modeling.
• Developing and training a self-supervised learning model.
• Evaluating model performance using simulations and experimental data.
• Transitioning from task-specific to foundation model.
• Benchmarking against state-of-the-art techniques.
• Preparing progress reports and scientific publications.
• Presenting results at conferences.

Connaissances

Machine learning

Applied mathematics

Image processing

Python programming

Description du poste

Organisation/Company CNRS Department Institut des Sciences Moléculaires d'Orsay Research Field Physics Researcher Profile First Stage Researcher (R1) Country France Application Deadline 1 Dec 2025 - 23:59 (UTC) Type of Contract Temporary Job Status Full-time Hours Per Week 35 Offer Starting Date 1 Feb 2026 Is the job funded through the EU Research Framework Programme? Horizon 2020 Is the Job related to staff position within a Research Infrastructure? No

Offer Description

The NanoBio team develops novel fluorescence microscopy modalities that push the limits of observation, both in terms of acquisition speed and imaging depth, with applications ranging from biology to the study of nanomaterials.

These developments sit at the crossroads of multiple disciplines, involving expertise in optics, electronics, image and data processing, chemistry, and biology.
With the support of several European funding programs, the team is building a data science and machine learning group to drive innovation across the various microscopy-related fields.
The position is therefore particularly suited for candidates who wish to work at the heart of this interdisciplinarity, with training in one of these major domains and an interest in exploring the others.

The recruited candidate will contribute to various aspects of the project. Depending on their background and expertise, they will take a leading role in one of the activities.

Throughout the project, the main tasks will include:

• Assessing the theoretical performance of the system through modeling,
• Developing and training a self-supervised learning model,
• Evaluating model performance using both simulations and experimental data,
• Transitioning from a task-specific model to a foundation model,
• Benchmarking results against state-of-the-art techniques,
• Preparing progress reports and/or scientific publications,
• Presenting results at national and international conferences.

This work will take place at ISMO (a joint CNRS / Université Paris-Saclay research unit) as part of the ERC project TimeNanoLive, within the interdisciplinary NanoBio team.
The laboratory is equipped with an on-site cell culture facility and several single-molecule localization microscopes.
The contract duration can be extended.

Technical skills are expected in machine learning, applied mathematics, or image processing, combined with advanced programming proficiency in Python.
The ideal candidate will have previous experience in machine learning, particularly in self-supervised learning. They should have knowledge of, or experience with, unlabeled data problems, pretext tasks, and approaches related to pre-training, transfer learning, and fine-tuning.
Beyond technical expertise, the candidate is expected to show a strong interest in the scientific implications of machine learning. They should be able to communicate regularly about their work and demonstrate a genuine enthusiasm for teamwork and interdisciplinarity.