Passionate about making ideas a reality? Join our welcoming world of tech and let your ideas soar.

Your role

Background

As the complexity of modern network infrastructures grows, so does the challenge of ensuring that network configurations are correct, efficient, and secure. With the rise of Software Defined Networking (SDN) and programmable data planes, large-scale networks can be dynamically reconfigured to meet operational needs. However, managing such configurations manually introduces the risk of errors, inefficiencies, and security vulnerabilities. This is especially critical in environments where connectivity rules, firewall policies, and redundancy requirements must be strictly enforced across hundreds of devices and multiple Virtual LANs (VLANs).

This master’s thesis project aims to explore how Large Language Models (LLMs) can be leveraged to automatically generate network configurations that fulfill complex, predefined rules. These rules will govern which devices can communicate, the routing between them, firewall enforcement, and ensuring redundancy through multiple network paths. The solution will need to scale across programmable switches and large network environments while ensuring that generated configurations are validated and error-free through automated testing in a simulated environment.

Description of the master thesis

• Researching methods to fine-tune LLMs for network configuration generation, ensuring compliance with pre-defined connectivity, security, and redundancy rules.
• Designing an automated validation system that tests the generated configurations against connectivity, firewall, and redundancy requirements.
• Implementing a prototype that generates and tests configurations in a network simulation environment such as Mininet or using programmable switches like Tofino.
• Optimizing the configuration generation to minimize errors while ensuring scalability in large, multi-VLAN networks with 70-80 devices and up to 20 VLANs.
   

The expected outcome is a proof-of-concept system where LLM-generated network configurations are automatically validated, reducing the manual effort required in network setup while minimizing human error and ensuring policy compliance.

Your profile

This project is suitable for a master’s student in computer science, electrical engineering, or related fields.

You should have:

• Strong knowledge of networking principles, including SDN, VLANs, routing, and firewalls.
• Programming skills in Python or a similar language, with experience in network simulation environments such as Mininet being a plus.
• A solid understanding of machine learning and experience with LLMs or neural networks is advantageous.
• Analytical skills and the ability to work independently to solve complex problems.

This position requires that you pass a security vetting based on the current regulations around/of security protection. For positions requiring security clearance additional obligations on citizenship may apply.

What you will be part of

Behind our innovations stand the people who make them possible. Brave pioneers and curious minds. Everyday heroes and inventive troubleshooters. Those who share deep knowledge and those who explore sky-high. And everyone in between.  ​
 

Joining us means making an impact together, contributing in our own unique ways. From crafting complex code and building impressive defence and security solutions to simply sharing a coffee with a colleague, every action counts. We encourage you to take on challenges, to create smart inventions and grow in our friendly and tech-savvy workspace. We have a solid mission to keep people and society safe.
 

Saab is a leading defence and security company with an enduring mission, to help nations keep their people and society safe. Empowered by its 23,000 talented people, Saab constantly pushes the boundaries of technology to create a safer and more sustainable world.
 

Saab designs, manufactures and maintains advanced systems in aeronautics, weapons, command and control, sensors and underwater systems. Saab is headquartered in Sweden. It has major operations all over the world and is part of the domestic defence capability of several nations. Read more about us here
 

Kindly observe that this is an ongoing recruitment process and that the position might be filled before the closing date of the advertisement.

Last application day

2024-11-30

Contact information

Patrik Johansson, Manager

Tel +46 (73) 418 2119

E-mail: patrik.pj.johansson@saabgroup.com

Mandar Joshi, Master thesis supervisor

Tel +46 10 217 0908

E-mail: mandar.joshi@saabgroup.com