The Foundation is looking for a proactive and dynamic young candidate with good organizational and relational skills and an inclination for teamwork, strongly motivated to work on innovative projects featuring strong technological components.
We can offer an important training opportunity to experiment with Federated Learning in Edge Computing scenarios. Federated Learning is showing its potential to strongly exploit capable devices to locally train AI models (mainly neural networks, but not only) using the information coming from the environment, then aggregate models to make a more general one. This paradigm can be applied to heterogeneous scenarios with different families of devices like MCU-based devices, GPUs, Single-board computers, etc.
The OpenIoT research group of the Digital Industry Center proposes to design, develop, and validate the architecture and a prototype of a federated learning scenario with heterogeneous devices.
The final goal of the internship is
- Analysis of the state of the art of heterogeneous edge computing and federated learning frameworks and scenarios;
- Understanding the development of ML applications on embedded devices (e.g., on ESP32);
- Adaptation and development of a working scenario with heterogeneous devices (ESP32 and NVIDIA Jetson Nano);
- Evaluation of real-world scenarios and benchmarking data;
- Ongoing Academic background in science and engineering fields (e.g., industrial automation, control systems and simulation, physics, math, computer science, computer engineering).
- Knowledge of concepts of machine learning and deep learning (nice-to-have experience with TensorFlow, TFLite, Keras libraries).
- Basic knowledge of embedded software development, like Arduino (nice-to-have experience with esp-IDF framework).
- Experience with distributed version control systems (git).
- Experience in Linux environment (shell scripting, package installation).
- Experience in programming languages for different platforms (Python, C, C++).
- Curricular internship (no allowance);
- 3-6 months, depending on the candidate's needs and preparation;
- Support for the search for accommodation at the affiliated structures.
The internship may be useful to complete the master's thesis.
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.
Applications will be reviewed as they arrive. Preferred period: at the earliest possible.
For any information, contact Massimo Vecchio (firstname.lastname@example.org).
For any support, further clarification and/or information, the Human Resources Department will remain available via the address: email@example.com