Job opportunities

Centres Inria associés

Type de contrat

Convention de stage/Internship agreement

Contexte

The successful candidate will join a dynamic and international research team at IMT Atlantique, Nantes (https://stack.inria.fr). As a research intern, you will contribute to the design, implementation and validation of agentic services for data-driven applications across Device-Edge-Cloud computing infrastructures. 
Edge intelligence enhances AI capabilities by bringing computation closer to data sources (e.g., IoT, vehicles), improving latency, bandwidth usage, privacy, and responsiveness. Traditional edge AI approaches typically involve static models and centralized orchestration. In contrast, Agentic AI empowers decentralized agents to adapt, reason, and act autonomously based on local context and evolving workloads — an emerging paradigm for truly general edge intelligence.
The successful candidate will be supervised by Daniel Balouek (Inria STACK, IMT Atlantique).
This work will be conducted as part of the QUICK project (_Collaborative services for Urgent systems across the Edge-Cloud Computing Continuum_, 2025-2027), funded by the "Etoiles Montantes" regional award.

Mission confié

The internship will focus on computation offloading, task scheduling, and adaptive resource allocation. Baseline methods (heuristics and classical ML-based approaches) will be implemented first. These will be extended using agentic AI techniques such as reinforcement learning and multi-agent systems, where each edge node acts as an autonomous agent observing its local state and optimizing decisions based on learned policies.

Principales activités

Define, implement, and evaluate agentic behaviors for distributed edge nodes, leveraging scalable experiments on the Grid’5000 testbed and algorithmic insights from Edge-Cloud operations, incorporating:
<ol>
<li style="font-weight: 400;">Survey Edge Intelligence operations such as computation offloading, data pipelines and on-edge learning to extract key algorithmic techniques and metrics. </li>
<li style="font-weight: 400;">Define agentic AI behaviors (state, actions, reward) suitable for edge resource management;</li>
<li style="font-weight: 400;">Develop agentic policy models using reinforcement learning (RL) or multi-agent reinforcement learning (MARL) to autonomously decide:</li>
</ol>
<ul>
<li style="font-weight: 400;">when and where to offload tasks,</li>
<li style="font-weight: 400;">how to allocate resources,</li>
<li style="font-weight: 400;">how to adapt to network variability</li>
</ul>
     4. Evaluate:
<ul>
<li style="font-weight: 400;">Latency and throughput improvements over baseline strategies.</li>
<li style="font-weight: 400;">Energy/CPU utilization and stability under load.</li>
<li style="font-weight: 400;">Agent adaptability to changing workloads & link conditions</li>
</ul>
 
<h2>References</h2>
Daniel Balouek-Thomert, Ivan Rodero, and Manish Parashar. Harnessing the computing continuum for urgent science. SIGMETRICS Perform. Eval. Rev., 48(2) :41–46, November 2020.
Zhang, Ruichen, Guangyuan Liu, Yinqiu Liu, Changyuan Zhao, Jiacheng Wang, Yunting Xu, Dusit Niyato et al. "Toward edge general intelligence with agentic AI and agentification: Concepts, technologies, and future directions." arXiv preprint arXiv:2508.18725 (2025).
 S. Ilager et al., “Proteus: Towards Intent-driven Automated Resource Management for Edge Sensor Nodes,” in 14th Workshop on AI and Scientific Computing, 2024.

Compétences

Cloud Computing, Edge Computing, Distributed systems
Python, Docker/Kubernetes
Reinforcement learning
Knowledge of sequential decision-making (MDP, influence diagrams, bandits, etc.)
Be independent and curious about research
Have an excellent level in English (spoken and written)
Multi-agent systems and/or Knowledge of the Grid '5000 testbed are a plus.

Référence

2025-09682

Thème

Distributed Systems and middleware

Domaine d'activité

System & Networks

Agentic AI for Edge Computing Intelligence