Exploratory Research in Generative Models

Investigate and advance state-of-the-art diffusion and score-based generative models with a focus on mathematical efficiency.

Conduct deep theoretical analysis of computational bottlenecks in sampling, denoising, and likelihood estimation.

Develop novel solver methods for diffusion ODEs/SDEs that are mathematically compatible with quantum algorithms.

Quantum-Classical Hybridization

Identify mathematical structures in generative models (e.g., linear algebra subroutines, probabilistic flows) amenable to quantum speedup.

Prototype hybrid workflows where quantum subroutines accelerate classical pipelines, using simulation or hardware access.

Rigorously benchmark theoretical versus practical advantages, producing white papers and internal technical reports.

Academic & Industrial Impact

Publish your findings in top-tier conferences (NeurIPS, ICML, ICLR, QIP) and journals.

Collaborate with quantum hardware teams to inform future architecture requirements based on algorithmic needs.

Translate research insights into scalable proof-of-concept implementations that can be handed off to engineering teams.

Quantum-AI Postdoctoral Fellow

Responsibilities