<aside>
ShiftElec is looking for its future researcher to develop and deploy non-intrusive electricity consumption monitoring technology in industry!
</aside>
<aside>
📅 6**-month fixed-term contract**, starting summer 2026
📍 SAMOVAR Laboratory, Télécom SudParis, Institut Polytechnique de Paris.
👤 PhD in AI or Engineer with 3+ years of R&D experience
🖥️ Hybrid: On-site (Belfort-Montbéliard and/or Palaiseau-Evry-Paris and/or Brussels) and remote.
💰 Salary according to profile and experience
🤝 You will work with:
As a postdoctoral researcher or research engineer, you will contribute to developing, testing, and deploying an initial prototype for non-intrusive load monitoring (NILM) in industrial environments.
NILM makes it possible to estimate the energy consumption of individual pieces of equipment by analyzing only the aggregate measurements of the main meter, without installing sensors on each device. This field of research is experiencing a surge of interest with the application of modern deep learning architecture and fine-tuning and transfer learning strategies.
Although widely studied in the residential sector, the industrial application of NILM remains less developed, with the result that both the available datasets and state-of-the-art methods are poorly suited to industrial applications.
The objective of this fixed-term contract is to propose new NILM methods for industrial applications and demonstrate their performance on real datasets. The work may focus in particular on integrating features specific to data from industrial meters into existing architectures, or on fine-tuning models pre-trained on non-industrial (residential, tertiary) datasets.