My research interests lie at the intersection of optimization, learning, and simulation techniques for large-scale, real-world decision-making. I use quantitative methods (e.g., mixed-integer and stochastic programming, decomposition methods, meta-/hyperheuristics) alongside machine learning models (e.g., deep learning, reinforcement learning, structured prediction, and graph models) to create efficient, robust, and scalable decision-support systems. My work is bifurcated into two trajectories: (1) ML-augmented optimization and (2) end-to-end optimization learning. By leveraging advanced algorithms, I aim to improve efficiency, reduce costs, and manage uncertainties in areas such as logistics, transportation, and sustainable supply/value chains, providing tangible benefits to industries and society.

Before my faculty position, I was an IVADO-COSMO Postdoctoral Fellow at McGill University, collaborating with Roussos Dimitrakopoulos at the COSMO Lab on data-driven lifelong learning stochastic optimizers for decision-making under uncertainty. The project, titled “Smart Mineral Value/Supply Chains”, is generously funded by the COSMO Consortium and the IVADO Strategic Research Funding Program “Integrated Machine Learning and Optimization for Decision Making under Uncertainty”, led by Erick Delage, Yossiri Adulyasak, and Emma Frejinger.

I received my Ph.D. in Mathematics from Polytechnique Montréal, where I worked on combining artificial intelligence and mathematical programming for airline crew scheduling under the supervision of François Soumis and Simon Lacoste-Julien, in GERAD & Mila. Prior to that, I completed a dual degree Maîtrise (M.Sc. equivalent) in Applied Mathematics at Polytechnique Montréal, and an Engineering Diploma from the Grenoble Institute of Technology, with a triple major and double minor, graduating with the highest honors.