Master Thesis: AI-based Transmitter

Join our Team
About this opportunity
As 5G evolves toward 6G, radio transmitters must meet increasingly stringent Error Vector Magnitude (EVM) and spectral efficiency requirements-while at the same time minimizing power consumption, area, and cost. Traditional transmitter chains rely on multiple standalone radio functions that are often optimized independently, leading to growing system complexity and expensive hardware implementations.
Recent advances in AI/ML-based signal processing open the possibility of replacing or optimizing multiple traditional DSP functions with a learning-based solution. By jointly addressing nonlinearity, impairments, and spectral performance, neural radio functions may achieve superior performance at comparable hardware and power cost.
This thesis will investigate whether such AI-native radio architectures can:

• Outperform legacy DSP-based solutions
• Be efficiently implemented on real hardware
• Meet future 6G transmitter requirements

If you are interested in AI for wireless systems, hardware design, and next-generation radio architectures, this thesis offers a unique hands-on opportunity at the intersection of communications, machine learning, and hardware.
What you will do
As a thesis student, you will:

• Design an optimized transmitter function that jointly handles key radio impairments traditionally addressed by multiple blocks, and explore novel ML architectures that offer better EVM, spectral performance, or robustness than legacy solutions.
• Implement and compare AI-based and traditional DSP-based radio functions on hardware, including:
  
  • Targeting FPGA platforms, utilizing both programmable logic and processors
  • Exploring and comparing architectural trade-offs
• Quantitatively evaluate AI vs. legacy implementations in terms of:
  
  • EVM and spectral performance
  • Latency
  • Power consumption
  • Hardware complexity and scalability
• Build a hardware test setup integrating digital, mixed-signal, and analog components, and demonstrate the solution under realistic laboratory conditions.
• Present your results and deliver a handover report to the Ericsson team at the end of the thesis.

The skills you bring
You are curious, collaborative, and eager to learn new things, and you enjoy working in a team to solve challenging research problems.

• Final-year MSc studies in electrical engineering, systems-on-chip, mathematics, machine learning, or a similar field
• Background in signal processing or radio (preferred)
• Interest in wireless communication systems, hardware implementation, and AI/ML-based signal processing

Extent: 1-2 students
Location: Lund
Why join Ericsson?At Ericsson, you'll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what's possible. To build solutions never seen before to some of the world's toughest problems. You'll be challenged, but you won't be alone. You'll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply? Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Lund
Req ID: 783099