AI Research Intern - Time Series Anomaly Detection for Sonar Data

The Internship In Short

Join the artificial intelligence team at MULTITEL and contribute to the development of advanced AI 
algorithms for underwater mine detection. During this internship, you will explore state-of-the-art 
anomaly detection methods to identify buried mines in sonar echo data. You will work on real-world 
signal processing challenges and contribute to research aimed at improving the reliability of 
sonar-based detection systems.

The topic

The SBSS (Sub-Bottom Scanning Sonar) project aims to develop a sonar-based system for the real-time, reliable detection of Unexploded Ordnance (UXO). The core challenge and specific focus of this initiative is the detection of mines buried beneath the seabed (0–3 m depth). While conventional systems provide broad coverage, they are limited by high false-alarm rates and reduced effectiveness against (partially-)buried targets. Within this framework, MULTITEL is responsible for developing advanced artificial intelligence algorithms to enhance mine detection and recognition. Previous research at MULTITEL has demonstrated the potential of machine learning for anomaly detection applied to individual sonar echo beams, where normal data corresponds to seabed-only returns and anomalies correspond to echoes interacting with buried objects (Mine-Like Echoes, or Milecs).

What you will work on:

You will explore several research questions, including:

• How do signal processing techniques and feature extraction methods influence the performance of anomaly detection algorithms on sonar echo data?
• Which anomaly detection methods are best suited to identifying mine-like echoes in sonar data?
• Can deep learning architectures improve the detection of anomalous sonar echo beams compared with conventional machine learning approaches?

As an intern, you will play an integral role in advancing MULTITEL’s research on AI-based underwater mine detection. Responsibilities include:

• Conducting a state-of-the-art literature review on anomaly detection, with a focus on sonar and time series data;
• Preprocessing and analyzing sonar echo beam data;
• Designing, implementing, and experimenting with anomaly detection methods, including deep learning architectures;
• Evaluating and comparing the performance of the investigated approaches for detecting anomalous sonar echo beams;
• Documenting the methodology, experiments, and findings in a comprehensive report;
• Presenting the results to the MULTITEL AI group.

The profile we are looking for:

We are looking for a motivated student who is curious about AI research and enjoys turning ideas into working solutions.

You should have:

1. A background in Computer Science, Artificial Intelligence, Data Science, or a related field, typically through an engineering degree or university program.
2. A strong interest in Machine Learning and Deep Learning, particularly in anomaly detection.
3. Fluency in English is mandatory; proficiency in French is a plus.
4. Experience with AI projects.
5. Good programming skills in Python.
6. Knowledge of PyTorch or another deep learning framework.
7. An interest in signal processing and time series analysis, including methods for preprocessing signals and extracting relevant features.
8. Basic knowledge of Git and software version control.
9. Working proficiency with Linux and Docker is a plus.
10. A self-starter mindset, with the ability to work both independently and as part of a team.
11. A curious and analytical approach to solving complex problems.
12. Attention to detail and commitment to producing robust, reproducible results.

Even if you don’t check every box in our requirements, we encourage you to apply. We value diverse backgrounds, curiosity, and the drive to learn, grow, and achieve.

Recruitment Process:

1. Application Review

We review your CV and cover letter to assess your background, skills, and interest in the internship topic.

2. Interview

Selected candidates are invited to an interview combining a technical discussion with a conversation about the internship objectives, your interests, and your expectations.

3. Following the interview

We select the candidate whose profile and interests best match the internship.