Machine Learning & Signal Processing Scientist (Hybrid)

About the Role We are looking for a skilled and motivated Machine Learning & Signal Processing Scientist to join our team. In this role, you will work on processing and analyzing multi-source environmental and sensor data, including satellites, drones, and in-situ measurements. Your work will focus on extracting meaningful signals from noisy data, developing robust algorithms, and modeling physical phenomena using advanced statistical and Machine Learning techniques.

Responsibilities:
Key Responsibilities
* Process and analyze multi-source sensor data, with a strong focus on noise reduction and signal quality improvement
* Develop and apply time series models to characterize and predict signal behavior
* Design and implement Machine Learning and deep learning models (e.g., CNNs, RNNs) for spatial and temporal signal analysis
* Build algorithms for detection, classification, and quantification of physical phenomena
* Validate models against real-world data and ensure scientific robustness
* Communicate results clearly through visualizations, reports, and presentations to technical and non-technical stakeholders
* Collaborate closely with cross-functional teams to refine and deploy solutions Qualifications
* 3+ years of experience in signal processing and Machine Learning
* Strong expertise in:
* Noise filtering and signal enhancement
* Time series analysis and modeling
* Experience with Machine Learning and deep learning frameworks
* Familiarity with multi-source sensor data (satellite, drone, or in-situ measurements)
* Experience with remote sensing data, including multispectral and hyperspectral imagery
* Strong programming skills in Python (or equivalent)
* Excellent problem-solving skills and attention to detail
Advantage
* Experience with generative AI or advanced representation learning
* Advantage, use of AI/ML Agents (Claude Code) for enhancing productivity
* Background in geospatial analysis or environmental data Education MSc in Physics, Geophysics, Earth Sciences, or a related scientific field (PhD is an advantage)
Job type:
Hybrid