Role Description
The Ionosphere and GNSS
The ionosphere remains one of the largest error sources in GNSS. At u-blox, we are advancing next-generation receiver technologies that intelligently mitigate these effects using data-driven models.
Role Overview
We are looking for an AI/ML intern to help model ionospheric Total Electron Content (TEC) behavior and generate practical correction strategies that enhance positioning performance across diverse environments and operating conditions.
What you’ll work on
* Design and implement AI/ML models to predict ionospheric TEC corrections for real receiver applications.
* Learn and model spatio-temporal patterns from GNSS measurements, TEC maps, and space-weather indicators.
* Explore and benchmark modern sequence modeling approaches (e.g., LSTM/GRU, Temporal CNNs, Transformers).
* Evaluate how learned corrections improve positioning accuracy and robustness under varying conditions (latitude, time-of-day, solar activity).
* Collaborate with experts in positioning algorithms, signal processing, and cloud-based data workflows to integrate models into realistic processing pipelines.
**Qualifications**
* MSc student (or late-stage BSc) in Machine Learning, Data Science, Electrical Engineering, Physics, Aerospace/Geospatial Engineering, or similar.
* Strong Python skills and experience with PyTorch or TensorFlow.
* Interest in GNSS, space weather, or signal processing (prior deep domain expertise not required).
* Analytical mindset, curiosity, and ability to communicate technical findings clearly.
What you’ll gain
* Hands-on experience applying AI to real satellite navigation challenges.
* Exposure to GNSS receiver development and large-scale positioning datasets.
* Mentorship from experts in navigation algorithms and signal processing.
* Opportunity to contribute to technology used in millions of connected devices worldwide.
This internship can be carried out in either Reigate (UK) or Tampere (Finland); you should be living and/or studying in either the UK or Finland to apply.