ML Engineer Intern: Antenna Digital Twins & Stability

Greenerwave; Paris; Presencial; EUR 11.000 - 18.000; A tiempo parcial

Ventajas ofrecidas por este puesto de trabajo

Lunch contribution

CSE benefits

Office in Paris 2nd arrondissement

Monthly team events

Mentorship from internship supervisor

Descripción de la vacante

Greenerwave seeks an ambitious final-year engineering student to join our team in Paris as an internship in modelling and training stability for digital twin antennas. You will explore physics-based models, train them, and learn to compare approaches with controlled experiments.

You’ll work with Algorithms and Modelling, RF and Software teams, document results, and grow your skills in Python, PyTorch, and numerical optimisation while contributing to robust, reproducible research in a

Formación

• Final-year engineering student in applied mathematics, simulation or modelling.
• Experience with optimisation or calibrating models using experimental data is a plus.
• Strong Python skills and familiarity with PyTorch or similar tool.

Responsabilidades

• Understand physics-based antenna models and how they are trained.
• Diagnose and improve stability by evaluating projection, reparameterisation or penalties.
• Improve stopping criteria, initialisation and reuse of trained models.
• Test code, document data and training conditions for reproducibility.

Conocimientos

Python programming

Optimization

Linear algebra

Teamwork

Educación

Final-year engineering student

Herramientas

PyTorch

Git

Linux

GPU computing

Descripción del empleo

Greenerwave seeks an ambitious final-year engineering student to join our team in Paris as an internship in modelling and training stability for digital twin antennas. You will explore physics-based models, train them, and learn to compare approaches with controlled experiments.

You’ll work with Algorithms and Modelling, RF and Software teams, document results, and grow your skills in Python, PyTorch, and numerical optimisation while contributing to robust, reproducible research in a