Born from an electric impulse, with smart connectivity and mindful technology, we empower clinical scientists in the fight against cardiovascular diseases. Yet, the best research and diagnostic tool, Magnetic resonance imaging (MRI) is used too rarely, and too often as a last resort when other techniques fail. Epsidy is addressing technological and practical issues with cardiac MRI.
Epsidy is a dynamic young start-up co-founded by engineers and PhDs, with a solid scientific culture and decades of combined experience. Epsidy focuses on the development of MRI-compatible instrumentation for better diagnosis and more effective therapy. Epsidy is in a close-knit relationship with the IADI Lab , and parts of any Epsidy position include regular exchanges with researchers. Epsidy core values are ownership, trust, and curiosity.
Within the Design and Development team (DND), you will be responsible for the development of new Epsidy product features. You will design, develop and test efficient frameworks to analyze and enhance electrocardiograms (ECG) acquired during MRI exams. One of the key aspects is to design similarity metrics comparing reconstructed and reference signals to fit real-time requirements of triggered cardiac imaging. Your main missions will be:
Medtech being a regulated environment, you will be documenting various aspects following Epsidy Quality Management System.
You demonstrated curiosity, rigor and autonomy during your education curriculum. You have developed software for various applications, in various languages, in the course of your studies as well as extra-curricular activities (reference required). You enjoy discovering new programming languages and are not afraid of tackling complex problems. You know common programming languages such as Python, Java, C or C++. You also are familiar with the concepts of Git, Dockers, and API.
Send 1-page CV + 1⁄2 page motivation letter to email@example.com, referencing 2024-INT-DND-SW.
Ideal start date: Early 2024. Competitive retribution.
 K. Isaieva, M. Fauvel, N. Weber, P. Vuissoz, J. Felblinger, J. Oster and F. Odille, A hardware and software system for MRI applications requiring external device data, Magnetic Resonance in Medicine, 88, 1406-1418, 2022.
 H. Wu, B. Salzberg, G. C Sharp, S. B Jiang, H. Shirato and D. Kaeli, Subsequence matching on structured time series data, International Conference on Management of Data, 682-693, 2005.
 Z. Wang, Time series matching: a multi-filter approach, New York University, 2006.
 W. Han, J. Lee, Y. Moon and H. Jiang, Ranked subsequence matching in time-series databases, International Conference on Very Large Databases, 423-434, 2007.
 L. Kegel, C. Hartmann, M. Thiele and W. Lehner, Season- and trend-aware symbolic approximation for accurate and efficient time series matching, Datenbank Spektrum, 21, 225--236, 2021.
 Q. Liu and H. Xue, Adversarial spectral kernel matching for unsupervised time series domain adaptation, International Joint Conference on Artificial Intelligence, 2744-2750, 2021.
 Y. Tong, J. Liu, L. Yu, L. Zhang, L. Sun, W. Li, X. Ning, J. Xu, H. Qin, Q. Cai, Technology investigation on time series classification and prediction, PeerJ Computer Science, 8, e982, 2022.
 Y. Li, Z. Chen and X. Deng, Similarity matching of time series based on key point alignment dynamic time warping, International Conference on Software Engineering and Knowledge Engineering, 300-305, 2022.
 H. Li, Z. Liu and X. Wan, Time series clustering based on complex network with synchronous matching states, Expert Systems with Applications, 211, 118543, 2023.
(c) GdR 720 ISIS - CNRS - 2011-2022.