Internship Opportunity at E3DA Research Unit - Adaptive neural architectures for BCI

FBK is opening a new internship opportunity in the Energy Efficient Embedded Digital Architectures - E3DA research unit of DigiS research center. The Bruno Kessler Foundation is a research and innovation institution based in Trento. The Foundation operates in a plurality of disciplinary fields and aims to achieve excellence in science and technology through 2 science clusters, one dedicated to technology and innovation and one to humanities and social sciences, organized in 12 Research Centers, and with more than 450 researchers. For more information visit https://www.fbk.eu/it/chi-siamo/.

In this context, the E3DA research unit focuses on wireless resource-constrained embedded technologies with a system-level approach targeting energy efficiency and Artificial Intelligence (AI) embedding at the very edge. The activity spans from hardware–software development for low-power wireless smart sensing devices to power management techniques, low-power multi-hop wireless protocols, and on-board processing in resource-limited devices, with a focus on Edge AI algorithms on multiple sensor data types (e.g., images, audio, biosignals, and others). Current research also includes Brain–Computer Interface (BCI) technologies, addressing efficient processing of brain signals for real-time applications (neurogaming, support systems).

Internship Opportunity
The student will develop a low consumption architecture for real-time detection of BCI commands. The main goal is to generalize across subjects, tasks and time, thus adapting the model to inter-individual and inter-session differences.The architecture will be deployed and evaluated offline on a microcontroller unit (MCU) or IOT device (Raspberry, Jetson). The internship will be customized to suit the candidate's university major, research interests, and strengths.

Project Highlights
  • Develop a generalized architecture with state-of-the-art techniques for detecting multiple BCI commands and adjusting to individual differences;
  • Develop an explainability layer (XAI) to investigate the neuroscientific soundness of the model;
  • Deploy the model natively in resource-constrained environments (MCU, Raspberry, Jetson);
  • Optimize resource usage and energy consumption through experimental evaluation.

Required background
  • Academic background in Engineering, Physics, Mathematics, or related technical field;
  • Proficiency in object-oriented programming and Python;
  • Knowledge of neural networks and deep learning fundamentals;
  • Proficiency with at least one deep learning framework (PyTorch, Tensorflow, Keras);
  • Good English proficiency for academic comprehension, work and participation in meetings with other International students and researche.

Preferred
  • Experience with design of experimental tasks evaluation;
  • Understanding of biosignal processing techniques;
  • Knowledge of model optimization (quantization, pruning) and hyperparameters optimization;
  • Knowledge of embedded systems and MCU programming.

Additional Opportunity
This internship may be extended into a full research thesis for interested candidates.

We offer
  • Curricular internship;
  • 3-6 months, the opportunity can be extended for thesis upon request;
  • Canteen;
  • Support for the search for accommodation at the affiliated structures.
All interested parties are requested to fill in the online form, clicking on "Apply online", and attach the required documents in Pdfs format:
  • Curriculum Vitae;
  • Cover letter;
  • Reference letter (optional).
Applications will be reviewed as they arrive. Preferred period: Fall 2025 to winter 2026.
For any information, contact Michele Romani (miromani@fbk.eu).

For any support, further clarification and/or information, the Human Resources Department will remain
available via the address: jobs@fbk.eu