AI-driven silicon photonics circuits design

Supervisory team: Professor Goran Mashanovich, Dr. Milos Nedeljkovic and Dr. David Rowe

This PhD applies AI to inverse design, a method that works backwards from desired performance to generate efficient photonic circuits. You'll develop algorithms that intelligently explore vast design spaces, enabling compact, manufacturable light-based chips.

Are you a computer science or electronics engineering student excited by the idea of applying AI to solve real-world engineering challenges? This PhD offers a unique opportunity to bring your skills in machine learning and optimisation into the rapidly evolving field of photonics.

Photonics—the science of light-based circuits—is enabling breakthroughs in data communications, autonomous systems, healthcare, and environmental sensing. As demand grows for faster, more energy-efficient photonic integrated circuits (PICs), traditional design methods are reaching their limits. Inverse design flips the conventional approach: instead of manually crafting circuit layouts, we define the desired performance and let algorithms discover the optimal structure.

This project explores how advanced AI techniques - such as graph neural networks, reinforcement learning and generative models - can automate and accelerate this process, making PICs more compact, efficient, and easier to manufacture.

You’ll be part of a collaborative team working at the intersection of computer science, photonics, and fabrication. Your contributions will help develop tools that intelligently search vast design spaces, optimise layouts, and verify performance - all while learning from real-world data and simulations. What you’ll gain:

• experience applying AI to physical design problems
• access to rich datasets of photonic devices and circuits
• opportunities to work in one of Europe’s top academic cleanrooms and photonics labs
• training in photonic design, fabrication, and characterisation
• a supportive, interdisciplinary research environment

Whether you're passionate about machine learning, optimisation, or algorithmic design, this project offers a chance to apply your skills in a meaningful and impactful way.

Entry requirements:

You must have a UK 2:1 honours degree or its international equivalent.

Ideal for candidates in computer science, physics or electronic engineering interested in AI-driven design innovation.

Fees and funding:

Full scholarships include tuition fees, a stipend at the UKRI rate plus 10% ORC enhancement tax-free per annum for up to 3.5 years (totalling £22,858 for 2025/26, rising annually) and a budget of £4200 for things like conference travel. UK, EU and Horizon Europe students are eligible for scholarships. Chinese Scholarship Council funded students are eligible for fee waivers. Funding for other international applicants is very limited and highly competitive. Overseas students who have secured or are seeking external funding are welcome to apply.

How to apply:

Apply now

You need to:

• choose programme type (Research), 2026/27, Faculty of Engineering and Physical Sciences
• select Full time or Part time
• search for programme PhD ORC (7097)
• add name of the supervisor in section 2 of the application

Applications should include:

• your CV (resumé)
• 2 academic references
• degree transcripts and certificates to date
• English language qualification (if applicable)