Seras-tu la prochaine stagiaire de Deep Mine SAS ?
ML & Signal Processing Intern
Offre mise à jour le 10 novembre 2026
- Type d’offre :
- Stage dans le supérieur
- Durée :
- non indiqué
- Niveau d’expérience :
- non indiqué
- Salaire :
- non indiqué
- Entreprise :
- Deep Mine SAS
- Secteur :
- non indiqué
- Adresse
- 1 rue du Mail, 75002 Paris (2Eme Arrondissement)
Descriptif de l’offre
About Us
At Harmattan AI, we are a next-generation defense prime building autonomous and scalable defense systems. Driven by rigorous engineering developments of new defense products based on recent robotics and AI developments, we are on a steep growth trajectory. If you are interested in a career in a highly technical environment, thrive on pushing boundaries, and want to achieve ambitious goals, we would love to hear from you.
About the Role
Context
Harmattan AI is developing a drone-integrated Synthetic Aperture RADAR (SAR) system designed for Intelligence, Surveillance, and Reconnaissance (ISR) applications. Traditional satellite-borne SAR images undergo post-processing with autofocus algorithms to enhance image quality. However, conventional algorithms are inadequate for UAV-borne systems due to trajectory instability, transforming the autofocus challenge into a high-dimensional optimization problem.
Your mission
The goal of this internship is to explore and apply machine learning-based optimization methods to address the autofocus problem in UAV-borne SAR imagery. You will have access to real radar data collected from our prototype system to validate your approaches.
Activities
- Literature review: Conduct a comprehensive review of existing autofocus methods for drone-borne SAR systems and identify candidate optimization techniques applicable to our problem.
- Algorithm Implementation: Develop and implement various optimization algorithms based on the literature review and project requirements.
- Performance evaluation: Assess and compare the performance of the implemented methods using both simulated data and real radar data collected from our prototype.
- Documentation: Document all work performed, including methodologies, results, and conclusions.
- Flight Tests Participation: Actively participate in flight test sessions to gather real-world data and validate the effectiveness of the developed algorithms in operational conditions.
Cette offre ID iZRHNu39mR5GAvb6n a été publiée le 16 avril 2025 sur le site de notre partenaire, MyFuture.