Realtime Ultrasonic Imaging: Scalable Local Inversion

CEA; Saclay; Sur place; EUR 8 900 - 13 000; Plein temps

Résumé du poste

CEA's LIIDE laboratory in Saclay is seeking an intern to develop a physics-informed local inversion for ultrasonic imaging that scales to extended inspection areas while aiming for real-time operation. You will study reusable structures across neighboring operators, work on overlapping reconstruction stitching, and explore parameter transfer across windows, with exposure to state-of-the-art equipment and a collaborative research environment.

The internship may lead to a scientific publication.

Qualifications

• Final-year master's student or engineering student in applied mathematics, signal processing or scientific computing.
• Strong Python programming and numerical optimisation skills.
• Experience with PyTorch and ultrasonic imaging is a plus.

Responsabilités

• analyse the spatial regularities and the low‑rank or spectral structure of local operators;
• design overlap and stitching strategies for neighbouring reconstruction windows;
• investigate parameter-transfer rules across windows;
• optimising the implementation.

Connaissances

Python programming

Numerical optimisation

Inverse problems

Signal processing

Formation

Master's degree / final-year student in applied mathematics or related field

Outils

PyTorch

GPU computing

Parallel computing

Description du poste

CEA's LIIDE laboratory in Saclay is seeking an intern to develop a physics-informed local inversion for ultrasonic imaging that scales to extended inspection areas while aiming for real-time operation. You will study reusable structures across neighboring operators, work on overlapping reconstruction stitching, and explore parameter transfer across windows, with exposure to state-of-the-art equipment and a collaborative research environment.

The internship may lead to a scientific publication.