Visiting Student – NST –Zhuo, Agnus – 02.17.26

Argonne National Laboratory • Lemont, IL

1d

About The Position

Machine learning (ML) provides a powerful framework to enhance quantum control by enabling adaptive, data-driven optimization of control pulses in the presence of complex noise, drift, and hardware constraints. Instead of relying solely on analytic pulse design or gradient-based optimal control (e.g., GRAPE), ML models, such as reinforcement learning agents, Bayesian optimizers, or neural-network-based surrogate models, can learn the effective system dynamics directly from experimental data, including non-Markovian noise and control distortions. In real time, ML can update pulse parameters to compensate for frequency shifts, crosstalk, and amplitude nonlinearities, thereby stabilizing gate fidelities and reducing calibration overhead. Moreover, model-based ML approaches can infer Hamiltonian parameters and decoherence channels on-the-fly, enabling closed-loop quantum control and adaptive error suppression. When integrated with quantum error correction protocols (e.g., surface codes or bosonic encodings), ML-enhanced controllers can dynamically adjust syndrome extraction timing and feedback operations, pushing superconducting and hybrid qubit platforms toward higher coherence, lower latency control, and scalable fault tolerance. In this project, we will establish the integration of AI agent with the quantum control hardware to realize AI-enhance quantum optimal control.

Requirements

• Must be currently enrolled full-time at an accredited institution.
• Must be 18 years or older at the time the appointment begins.

What This Job Offers

• Job Type: Full-time
• Career Level: Intern
• Education Level: No Education Listed