About this role
Summary: This internship focuses on improving the robustness and reliability of machine learning models for antenna digital twins. The role involves investigating training stability, implementing optimization techniques, and ensuring reproducibility through controlled comparisons and documentation.
Why this role is key
The digital twins of our antennas are used to configure our technology to steer electromagnetic waves. These models combine a physical understanding of our antennas with trained parameters. This internship aims to further improve the robustness and reliability of our model training.
Reporting to Steph, Software Engineer, you will investigate the factors that can influence training stability and evaluate different approaches to improving it. Working with our Algorithms and Modelling, Radio Frequency and Software teams, you will learn to connect physical modelling, numerical optimisation and experimental analysis through controlled, reproducible comparisons.
Your responsibilities
Understanding the model and its training process
- Understand our physics-based antenna models and how they are trained,
- Reproduce a training run and measure the variability in the resulting performance.
Diagnosing and improving stability
- Set up monitoring of relevant quantities and automatically detect diverging training runs,
- Investigate and implement projection, reparameterisation or penalty methods to enforce model convergence at each optimisation step,
- Evaluate the impact of these methods on accuracy and computation time.
Optimising and comparing training runs
- Improve stopping criteria, initialisation and the reuse of previously trained models,
- Compare several model variants under controlled conditions,
- Analyse the model’s physical and numerical mechanisms to investigate their influence on the results,
Documentation and reproducibility
- Test the code developed and maintain it under version control,
- Document the data and training conditions to ensure reproducibility of the results,
- Present the methods investigated and the results obtained in reports supported by quantitative data.
### Profile
Interested in joining us ?
Don’t meet all the criteria? Apply anyway. Above all, we are looking for someone who is motivated, curious and ready to learn, within a team that will support their skills development. 😊
You are currently in your final year at an engineering school (or an equivalent university programme), specialising in applied mathematics, simulation or modelling. You have some initial experience in optimisation or in calibrating models using experimental data, and you are interested in wave physics.
Your technical skills
- You have a solid foundation in applied mathematics, particularly linear algebra and constrained optimisation,
- You can program in Python and have some initial experience with PyTorch or a similar tool,
- Knowledge of electromagnetism would be appreciated,
- Familiarity with Git or Linux, or experience with GPU computing, would be an additional asset,
- You have a good command of written and spoken English, enabling you to work in an international environment.
Your approach to work
- You enjoy working in a team and communicate easily with people from a variety of backgrounds,
- You are thorough and approach problems methodically,
- You enjoy exploring different approaches and proposing creative solutions to technical problems,
- You are curious and take the initiative to move your work forward,
- You can work independently while seeking support from the team when needed,
- If you use AI tools for coding, you critically assess the code and calculations they produce,
- You can write clear, well-structured documents to share your results and document your work.
Reasons to work at Greenerwave
- A financial contribution towards your lunches,
- Benefits offered by our Social and Economic Committee (CSE),
- Offices located in the heart of Paris, in the 2nd arrondissement,
- Monthly team events and evenings out to spend time together outside of project work,
- Discussions with technical teams to discover the technologies you are working on and better understand their applications,
- A multicultural environment bringing together people with varied expertise, where you can learn from others,
- Close guidance and support from your internship supervisor to help you progress throughout your internship and prepare to launch your career.
### Recruitment process
Our recruitment process
1. Your application is reviewed by the HR team, with no AI-based pre-screening.
2. An initial 20- to 30-minute phone call to discuss your background, your search and your expectations.
3. An interview with Elie, Algorithms & Modelling Team Leader and Steph, Software Engineer, to explore the internship responsibilities in more detail and discuss your technical skills and their practical application.
4. A final interview with a member of the HR team to get to know you better, discuss your approach to work and answer your questions.
Throughout the process, we keep you informed of the progress of your application and remain available to answer your questions. We provide feedback at every stage, with constructive insights to help you understand our decision.
*We welcome applications from people of all backgrounds, regardless of ethnicity, gender, age, sexual orientation, disability or religion. We value diversity and believe that everyone brings a unique perspective that enriches our team.*