Summary
Mohammad Shaelaie is a PhD candidate in Industrial Engineering at Lehigh University with five years of experience applying optimization, reinforcement learning, and graph neural networks to real-world decision problems. He designs hybrid algorithms that combine Branch & Bound and Deep RL to both improve agent learning and warm-start exact solvers, reducing tree sizes and speeding up solution times. Mohammad has taught a range of data science, algorithms, and optimization courses while mentoring students on simulation and pandemic modeling, and he contributes to open-source bilevel optimization tools such as BilevelJuMP.jl. His industry work includes large-scale railroad optimization and refueling problems where he cleaned raw data, built Gurobi models in Python/C++, and implemented decomposition methods. Comfortable bridging theory and practice, he brings uncommon expertise in making advanced ML models more interpretable for operational decision-making.
5 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD Industrial Engineering, Doctor of Philosophy - PhD Industrial Engineering at Lehigh University
Master of Science - MS Industrial Engineering, Master of Science - MS Industrial Engineering at Ferdowsi University of Mashhad