Job offer

[1] A. Boiano, N. Chukhno, Z. Smoreda, A.E.C. Redondi, M. Fiore, A First Look at Operational RAN Updates and Their Impact on Carrier Traffic Demands and Prediction, IEEE INFOCOM 2026

[2] M. Jabbari, A. Duttagupta, C. Fiandrino, L. Bonati, S. D'Oro, M. Polese, M. Fiore, T. Melodia, SIA: Symbolic Interpretability for Anticipatory Deep Reinforcement Learning in Network Control, IEEE INFOCOM 2026

[3] A. Duttagupta, M. Jabbari, C. Fiandrino, M. Fiore, J. Widmer, SymbXRL: Symbolic Explainable Deep Reinforcement Learning for Mobile Networks, IEEE INFOCOM 2025

[4] L. Schiavo, G. Garcia-Aviles, A. Saavedra, M. Gramaglia, M. Fiore, A. Banchs, X. Costa-Perez, CloudRIC: Open Radio Access Network (O-RAN) Virtualization with Shared Heterogeneous Computing ACM MobiCom 2024

[5] A. Collet, A. Bazco-Nogueras, A. Banchs, M. Fiore, Explainable and Transferable Loss Meta-Learning for Zero-Touch Anticipatory Network, Management IEEE Transactions on Network and Service Management, 21:3, 2024

[6] C. Fiandrino, E. Pérez-Gómez, P. Fernández-Pérez, H. Mohammadalizadeh, M. Fiore, J. Widmer, AIChronoLens: Advancing Explainability for Time Series AI Forecasting in Mobile Networks, IEEE INFOCOM 2024

[7] S. Alcala-Marin, A. Bazco-Nogueras, A. Banchs, M. Fiore, kaNSaaS: Combining Deep Learning and Optimization for Practical Overbooking of Network Slices, ACM MobiHoc 2023

[8] A. Collet, A. Bazco Nogueras, A. Banchs, M. Fiore, AutoManager: a Meta-Learning Model for Network Management from Intertwined Forecasts, IEEE INFOCOM 2023

[9] A. Collet, A. Banchs, M. Fiore, LossLeaP: Learning to Predict for Intent-Based Networking, IEEE INFOCOM 2022

[10] C. Zhang, M. Fiore, I. Murray, P. Patras, CloudLSTM: A Recurrent Neural Model for Spatiotemporal Point-cloud Stream Forecasting, AAAI 2021

[11] D. Bega, M. Gramaglia, M. Fiore, A. Banchs, X. Costa-Perez, AZTEC: Anticipatory Capacity Allocation for Zero-Touch Network Slicing, IEEE INFOCOM 2020

[12] D. Bega, M. Gramaglia, M. Fiore, A. Banchs, X. Costa-Perez, DeepCog: Cognitive Network Management in Sliced 5G Networks with Deep Learning, IEEE INFOCOM 2019

Master Degree or equivalent, The position requires:

• A degree in Computer Science or related field, with a solid academic record
• Excellent programming skills
• Background in fundamental and applied ML, preferably with pytorch
• A strong interest in working with massive network traffic data
• Fluency in written and spoken English
• Enthusiasm for interdisciplinary research.

Languages ENGLISH

The position offers:

• Hands-on training in applied AI for next-generation mobile network systems
• A unique opportunity to work with large-scale real-world measurement data
• The possibility to interact and collaborate with major telco industry players
• A vibrant, collaborative, multi-cultural and English-speaking environment
• The prospect of publishing at top-tier venues in networking
• An advantageous path to a successful career in industry or academia [13]
• The high quality of life of the region of Madrid, Spain, where we are based.

Eligibility criteria

Equal Employment Opportunity

The Networks Data Science group at IMDEA Networks Institute has an opening for one PhD student in the area of mobile network intelligence. The successful candidate will design original AI solutions for the automation of network functionalities to be deployed in next-generation 6G systems. The focus of the studies will be on surpassing practical limitations that affect today's AI paradigms and hinder their adoption in production-grade mobile network infrastructures. The PhD student will work in the context of on-going collaborations with leading MNOs such as Orange and Telefónica and take advantage of privileged access to Terabytes of measurements from real-world networks to (i) understand the very specific challenges of learning from network traffic, (ii) train original AI models that are designed to operate precisely on such data, and (iii) demonstrate the viability in production of AI-driven solutions for, e.g., KPI forecasting, RAN energy cost reduction, or anomaly detection-all of which are still largely open problems in 5G production networks. The NDS group has a notable history of breakthroughs in the design of AI for mobile network operation [1-12], which represents an ideal foundation for the student to make meaningful contributions to the field.