Master Thesis: AI-driven antenna design

Join our Team

About this opportunity

Join Ericsson for a master's thesis on how AI agents can design hardware autonomously. The agent interprets requirements, creates parametric geometry, launches electromagnetic simulations, evaluates results and decides the next design step. You will help build the AI harness behind it: design tools, simulation APIs, requirements, verification and run logs in one repeatable workflow.

The test case is the antenna-filter interface. Hardware is normally split into specialist domains, each block designed against a fixed interface such as 50 ohm at a reference plane. That keeps development manageable, but hides system-level trade-offs. An agent is not a specialist: it can judge connected parts together and accept a less ideal transition when that buys a shorter feed network, lower loss, fewer PCB layers or better amplitude and phase balance at the elements. How far this can be pushed is an open question: can an agent hold a full requirement set and converge on a design that meets it, and where does it stall?

What you will do

Deliver a digital proof of concept. Your work may include:

• Defining requirements, reference planes and metrics, and a baseline from separately designed hardware
• Modelling one bounded case: filter-to-antenna integration, a fan-in/fan-out network, or a contactless transition
• Building harness skills that create geometry, drive Ansys HFSS, CST or Ericsson tools through scripting APIs, and extract results
• Implementing agentic self-verification - geometry and mesh checks, rendered views, sanity limits, compliance - and logging that gives persistence to agents and lets a run be resumed
• Letting the agent trade across the interface, then comparing with a conventional design held to a fixed 50-ohm plane
• Applying manufacturability, clearance, layer-count and tolerance constraints

It concludes with a report and a presentation to Ericsson's hardware teams, and can lean towards the hardware or the harness.

The skills you bring

• Electrical engineering, engineering physics or similar with an electromagnetics background (antennas, filters, microwave) - or, for a second student, data science, computer science or machine learning
• Python, and a strong interest in AI agents, large language models and modern automation
• Curiosity about how far AI can push a design, and where supervision is still needed

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) || Stockholm

Req ID: 791402