Thesis: Achieving Ultra-Low Latency in Multi-Agent Systems
Join us for your thesis work! Gain hands-on experience, work on real projects, and develop your skills in a supportive and innovative environment!
High Level Description
The use of Multi-Agent Systems (MAS) and MCP tools creates a critical need for faster, more responsive solutions. High latency during inter-agent communication and tool execution is a major bottleneck. This project aims to combine LLM intelligence with alternate communication protocols to drastically reduce latency and enhance the efficiency of multi-agent workflows.
Project Description
This thesis explores how LLMs can intelligently orchestrate multi-agent solutions to achieve lower latency, especially when using MCP tools while utilizing A2A (Agent to Agent). You will focus on developing a secure and efficient solution for agents to collaborate and execute code in contained environments, prioritizing optimization to minimize round-trip calls and maximize parallel processing.
Key areas to explore include:
- Low-Latency Communication: Develop techniques like request batching or predictive tool allocation to eliminate communication delays between agents using MCP tools.
- Optimize A2A protocol communication.
- Optimized Orchestration: Design workflows where LLMs coordinate multiple agents to run tasks in parallel rather than sequentially, streamlining complex processes for maximum speed.
- Transparency: Create clear explanations of the system's optimization process ("how it saved time") to build user trust in high-speed AI tools.
- Your work will advance applications in areas like real-time digital assistants and high-speed cloud automation, where minimal delay is essential.
Who are we looking for?
We're searching for master's or bachelor students who’s passionate about AI, programming, and building something new. Knowledge about Typescript and Python is a bonus, but not necessary since if you’re comfortable with any programming language you should not have a problem jumping over to these.
You should also:
- Enjoy solving real problems and experimenting with new ideas.
- Be motivated to learn how AI and secure software go hand in hand.
- Be fluent in Swedish, written and spoken.
Purpose
We're trying to see what AI systems can really do, while making sure they're safe and effective. The plan is to mix great AI agent with sophisticated sandbox environments to achieve this.
An Exciting Journey with Knightec Group
Semcon and Knightec have joined forces as Knightec Group. Together, we are Northern Europe’s leading strategic partner in product and digital service development. With a unique combination of cross-functional expertise and a holistic business understanding, we help our clients realize their strategies – from idea to complete solution.
Practical Information
This is a thesis position, located at our office in Gothenburg. Start date 2026-01-20.
Please submit your application as soon as possible, but no later than 2025-11-30. If you have any questions, you are welcome to contact Felix Fredin. Note that due to GDPR, we only accept applications through our careers page.
- Business unit
- Thesis
- Role
- Master thesis
- Locations
- Göteborg
Already working at Knightec Group?
Let’s recruit together and find your next colleague.