Research Internship: World Models for Networking

inria; France; Hybrid; EUR 13,000 - 18,000; Full time

Benefits offered by this job

Partial reimbursement of public travel

Teleworking possible

Professional equipment available

7 weeks annual leave + RTT days

Social, cultural and sports events

Job summary

Inria is offering a temporary internship focused on advancing World Models in networking. The project explores adapting LeWorldModel to dynamic wireless networks and evaluating predictive representations.

The selected candidate will reproduce leading JEPA-based methods and tailor them to a networking context, with hands-on work in Python and PyTorch. The internship emphasizes research quality, experimentation, and reporting, and it offers teleworking possibilities and access to Inria's research

Qualifications

• Solid background in ML with practical experience in Python and PyTorch.
• Interest in networking (wireless networks a plus).
• Familiarity with self-supervised learning, representation learning or reinforcement learning is a plus.

Responsibilities

• Study the World Model and JEPA literature, then reproduce and test the LeWM model.
• Choose a suitable networking application and an input representation based on feasibility and relevance.
• Adapt and retrain the model on this application, possibly through a sequence of tasks of increasing complexity.
• Evaluate the results experimentally and analyze both the predictions and the learned representations.

Skills

Python

PyTorch

Machine Learning

Self-supervised learning

Education

Master's student in ML/CS

Job description

Inria is offering a temporary internship focused on advancing World Models in networking. The project explores adapting LeWorldModel to dynamic wireless networks and evaluating predictive representations.

The selected candidate will reproduce leading JEPA-based methods and tailor them to a networking context, with hands-on work in Python and PyTorch. The internship emphasizes research quality, experimentation, and reporting, and it offers teleworking possibilities and access to Inria's research