About this opportunity:
The key-value (KV) cache is a core optimization in transformer-based models. It accelerates token generation by reusing previously computed information instead of repeating the same computations.
Much of the existing research assumes fixed hardware and communication conditions. Mobile networks are dynamic: wireless links vary with fading and interference, congestion affects latency, and users move between base stations. During handovers, accumulated session state may need to be transferred or rebuilt.
This thesis will investigate KV cache management in mobile networks, considering user mobility, concurrent users, and wireless channel conditions.
What you will do:
The project will move from literature review to testbed development and systematic evaluation:
- Review the literature: Examine KV cache management for LLM inference, including load balancing, quantization and compression, prefix caching, and prefix-cache-aware request routing.
- Build a testbed: Simulate realistic mobile-network conditions, including time-varying wireless links, fading, interference, throughput and latency variation, congestion, user mobility, and handovers between base stations. Support multiple users sharing cache and network resources, different KV cache strategies, and different network traces.
- Evaluate strategies: Benchmark existing and proposed approaches, such as transferring versus rebuilding the cache during handover and mobility-aware prefix routing. Compare compute cost, latency, and energy efficiency across network conditions, and analyze the trade-offs.
- Report your findings: Write a thesis report and present your results at Ericsson Research.
You will also have the opportunity to propose and develop your own ideas within the project.
The skills you bring:
- You are pursuing a master's degree in Computer Science, Artificial Intelligence, Data Science, Electrical Engineering, Computer Engineering, or a related field.
- Strong programming skills in Python and PyTorch.
- Coursework or experience in AI; a background in machine learning and neural networks is preferred.
- Interest in AI research or building end-to-end AI prototypes.
- Knowledge of Git is an advantage; familiarity with network simulators such as ns-3 is beneficial.
- Fluency in English.
Application and Practical Details
Please include your CV, cover letter, and transcripts for both your bachelor's degree and current master's studies.
- Extent: One student, 30 ECTS credits.
- Preferred start: Spring 2027.
- Location: Ericsson Research, Stockholm.
- Keyword: KV cache.
Skills Required
- Pursuing a master's degree in Computer Science, Artificial Intelligence, Data Science, Electrical Engineering, Computer Engineering, or a related field
- Strong programming skills in Python
- Strong programming skills in PyTorch
- Fluency in English
- Coursework or experience in artificial intelligence
- Interest in AI research or building end-to-end AI prototypes
- Background in machine learning and neural networks
- Knowledge of Git
- Familiarity with network simulators such as ns-3
What the Team is Saying
.png)
.png)
What We Do
Ericsson builds the digital connectivity the world relies on. Our technology underpins the mobile networks, platforms, and systems that billions of people, businesses, and societies depend on every day. We are a global leader in communications technology, delivering mobile network infrastructure, cloud software, and wireless connectivity solutions for service providers and enterprises worldwide. Our networks support connectivity across 180+ countries, helping power everyday communication as well as critical digital services at global scale. Connectivity has evolved far beyond consumer mobile use. Today, nearly 80% of the world’s population accesses the internet via mobile networks, and Ericsson is helping shape what comes next. We are advancing 5G and 5G Advanced, developing network APIs that open connectivity to the global developer ecosystem, and applying automation and AI to make networks more intelligent, efficient, and resilient. Ericsson was the first company to launch live 5G networks on five continents, and our 5G platform is now commercially live in 150+ networks across 60+ countries. We also support more than 36,000 enterprise customers, enabling secure, high-performance connectivity for industries such as manufacturing, aviation, logistics, utilities, and public safety, where reliability and performance are mission critical. Innovation is central to how we work. Ericsson has approximately 28,000 employees in research and development, backed by one of the strongest intellectual property portfolios in the industry with 60,000+ granted patents. Our engineers, researchers, and technologists work across 100+ global R&D sites, helping define how networks evolve and how digital infrastructure is built for the long term. As the world moves toward a mobile-first, AI-powered, and cloud-driven future, connectivity becomes the foundation for digital transformation across every industry. Ericsson is building that foundation, shaping the future of digital connectivity through technology that operates at global scale and supports real-world impact, today and for what comes next.
Why Work With Us
Ericsson is a place for people who want to work on technology that powers everyday life. You’ll contribute to large-scale systems used every day, tackle complex challenges in live environments, and keep developing your skills and career in your own vision.
Gallery
.jpg)
.jpg)
.jpg)
.jpg)
.jpg)
Ericsson Offices
Hybrid Workspace
Employees engage in a combination of remote and on-site work.
Ericsson adopts a hybrid work model globally because we know balance matters. Sometimes things are better in real life. Other times we can be more productive at home. Our hybrid approach gives you the best of both worlds.
