Post-Doctoral Research Visit F/M Euro-3C : data management across computing continuum

Context
In the framework of the European project Euro-3C, launched in 2026, the STACK team is opening a postdoctoral position to address the challenges of data management across multiple storage systems belonging to several tenants. Funded at €75 million, the Euro-3C project is a large-scale initiative that aims to establish Europe's first large-scale federated Telco-Edge-Cloud infrastructure. By seamlessly integrating telecommunications networks, edge computing and cloud resources into a unified framework, the project will foster technological autonomy, reduce dependencies on non-European providers and enable the deployment of innovative digital services across multiple industrial sectors.
Further information at: https://euro-3c.eu and https://stack.inria.fr
Assignment
A central challenge in the transition from cloud to edge computing is enabling distributed applications—originally designed for cloud platforms—to capitalize on edge opportunities while mitigating the limitations of wide-area network links. To address this, the STACK team proposed federating modular microservice instances (one per edge site or tenant) and dynamically orchestrating collaborations among them for each request through a domain-specific language (DSL), managed transparently by the Cheops runtime. Having demonstrated the effectiveness of this approach on both OpenStack and Kubernetes, we now aim to extend it to distributed storage systems, enabling simple and transparent cross-location dataset management.
Within task T3.2 'Data Interoperability and Software Distribution Subsystems', led by Capgemini, STACK proposes to leverage the Cheops concept and deliver a CLI for DevOps teams to manage datasets across multiple domains (i.e., distinct REST-based storage services) by abstracting data locations at the CLI level. Such a tool will allow DevOps teams to manage the full lifecycle of datasets across the Euro-3C infrastructure.
Further information at:
https://inria.hal.science/hal-04522961v1 and https://gitlab.inria.fr/discovery/cheops/
Main activities
Phase 1:

• Understanding the Euro-3C reference architecture
• Getting up to speed on the REST APIs of major storage systems and on the APIs selected by the project (e.g., CAMARA)
• Familiarization with the Cheops concepts and analysis of the proof of concept built around the Redis system

Phase 2:

• Proposal of a proof of concept within Euro-3C for managing datasets across several independent systems
• Writing scientific papers presenting the design choices and their evaluation
• Contributing to the writing of deliverables in line with the expectations of task T3.2

Phase 3: (depending on the results of the two previous phases)

• Transfer of the solution to the Euro-3C system developed by the consortium's industrial partners
• Extending the proposal with automated loops to manage dataset lifecycle
• Integration with the "local-first" indexing system proposed by the STACK team

During all three phases, the successful candidate will participate in the project's regular meetings, notably those of WP1 and WP3. Attendance at plenary meetings across Europe is expected also.
Skills
Technical skills (required):
Knowledge on distributed file systems/distributed storages (Ceph, S3, IPFS, Redis, etc.)
Python, Go
Software engineering
Cloud/Edge
Technical skills (a plus):
Experiment driven research (Chameleon, SLICES, enoslib, etc.)
Kubernetes
Camara
Knowledge of softwarization of networks (NDN, SDN, NFV/NFC...)
Languages:
English (required for scientific dissemination)
French (a plus for interactions with acquisition sites)
Relational skills:
Strong organisational and coordination skills
Ability to work in a collaborative and interdisciplinary environment
Autonomy and initiative in managing field campaign