Machine Learning Internship – Rydberg-Based Quantum Simulators

Role Overview

• Develop and train Neural Quantum States (NQS + VMC), with pretraining of the NQS on datasets generated by the QPU.
• Benchmark this approach against established numerical methods (e.g., exact diagonalization, standard VMC, tensor networks) and against raw QPU data.
• Apply NQS to represent observables and many-body wavefunctions of magnetic Hamiltonians.
• Contribute to internal tools and publications.

Requirements

• Master’s or PhD student in quantum many-body physics.
• Proficiency in one or more programming languages such as Python or Julia.
• Demonstrated experience with machine learning methods applied to quantum many-body systems (e.g., neural quantum states, supervised and unsupervised ML, kernel methods).
• Experience with numerical methods for quantum spin systems (e.g., exact diagonalization and variational Monte Carlo).
• Familiarity with scientific computing frameworks (e.g., JAX, PyTorch, TensorFlow).
• Experience working in high-performance computing (HPC) environments.
• Ability to work collaboratively in a research team.
• Strong communication skills in English.

Tech Stack

• Python
• PyTorch
• Tensorflow

Benefits

• Hands-on experience with Pasqal’s analog QPU and emulator stack used to model such devices.
• The opportunity to learn key aspects of Pasqal’s quantum hardware.
• Mentorship from a multidisciplinary team (quantum many-body physics, machine learning, materials science).