This PhD project aims to develop an AI-driven platform for the autonomous fabrication of 2D quantum materials, enabling the on-demand engineering of strongly correlated phases by stacking and twisting atomically thin layers. By integrating machine learning, optical metrology, and quantum materials science, the project will explore how to program many-body Hamiltonians through precise control of twist angle, strain, displacement fields, and dielectric environment in moiré superlattices.
Key Objectives:
- AI & Machine Vision: Extend real-time detection and segmentation pipelines (Python/OpenCV/PyTorch) and train decision models to autonomously plan and adapt fabrication steps.
- Optical Metrology: Use photoluminescence, reflectivity, and second-harmonic generation to identify materials, assess interface quality, and determine twist angles.
- 2D Device Fabrication: Automate pickup, release, and alignment of monolayers with twist/strain control and contamination avoidance.
- Cryogenic Characterisation: Operate cryostats and perform low-temperature magneto-optical spectroscopy to probe minibands, interactions, and symmetry breaking.
- Quantum Materials Engineering: Link fabrication parameters to emergent quantum phases, using structured logging and digital twins to ensure reproducibility.
Training & Impact:
The student will gain interdisciplinary expertise in AI, quantum materials, optical spectroscopy, and cryogenic systems, contributing to the development of programmable quantum devices. The project supports fundamental discoveries in correlated insulators, superconductivity, and magnetism, and offers collaboration opportunities with academic and industrial partners.