AI/ML engineer in underwater acoustics

Optics11 is a deep-tech company developing cutting-edge fiber-optic sensing technologies for challenging environments, including underwater acoustics, offshore energy, and defense applications. Our systems enable high-performance sensing and monitoring through advanced photonics, signal processing, and data-driven intelligence. We are expanding our R&D team with a Senior AI/ML Engineer who combines strong mathematical foundations with applied machine learning expertise to enhance the next generation of intelligent acoustic sensing solutions.

• Develop and implement machine learning solutions for underwater acoustic sensing use cases, including detection, classification, localization and anomaly monitoring within fiber-optic sensing systems.
• Select and adapt modelling approaches based on data availability, operational constraints and system requirements.
• Apply strong foundations in applied mathematics, statistics and signal processing (e.g., beamforming, spectral analysis, detection pipelines) and integrate these with modern data-driven ML techniques.
• Design, train, evaluate and benchmark AI/ML models, ensuring robustness, generalization and deployment readiness.
• Validate models rigorously across laboratory experiments and offshore field datasets, with clear performance tracking and reproducible experimentation.
• Analyze and interpret large-scale experimental and real-world fiber-optic sensing datasets, contributing to scalable workflows for data preparation, labelling and augmentation.
• Support technical trade-offs between accuracy, interpretability, latency and real-time or embedded constraints.
• Collaborate closely with acoustics engineers, signal processing specialists, software and embedded teams to integrate ML components into operational acoustic sensing pipelines.
• Translate complex AI/ML results into clear technical insights that inform system-level engineering decisions.
• Contribute to strong engineering practices, including version-controlled experiments, documentation, traceability, validation standards and continuous improvement of ML components.
• Stay informed about advances in AI/ML for time-series analysis, sensor fusion and signal-informed learning, and prototype promising approaches that complement the broader technology stack.

• MSc in Machine Learning, Signal Processing, Applied Mathematics, Computer Science, Physics, or a related field.
• Strong foundation in linear algebra, probability, statistics, and signal processing.
• Proven experience applying AI/ML methods to time-series or sensor data, including techniques such as: Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs) (e.g., LSTMs), Transformer-based architectures for time-series learning.
• Supervised and unsupervised learning approaches for detection and classification.
• Hands-on experience with model training, evaluation, and validation in applied settings.
• Proficiency in Python and modern ML frameworks (e.g., PyTorch, TensorFlow, JAX).
• Ability to work in an applied R&D environment with experimental and field data, balancing model performance with real-world constraints.
• You'll be working with clients in the defense and security sectors, obtaining a Certificate of No Objection issued by the AIVD (Dutch General Intelligence and Security Service) is mandatory. This means you will need to undergo a security screening.
• Будет плюсом: Experience with underwater acoustics, sonar, or beamforming-related applications; Knowledge of embedded or real-time deployment constraints; Experience with sensor fusion, self-supervised learning, or physics-informed ML; Familiarity with offshore, defense, or industrial monitoring domains; Familiarity with structured ML development processes such as CRISP-ML(Q) or similar lifecycle and quality frameworks

• Competitive salary.
• Innovative high-tech, international organization.
• The opportunity to work in a cross-functional and interdisciplinary environment.
• A lot to learn and to develop, we stimulate personal development.
• Lunches.