Ph.D. Candidate · ÉTS Montreal
Marwen Kraiem
Reinforcement Learning · Operations Research · ML for Optimization
I am a Ph.D. candidate at École de technologie supérieure (ÉTS) in Montreal, working at the intersection of Machine Learning and Operations Research with a focus on Reinforcement Learning for combinatorial optimization under uncertainty.
Prior to my doctoral studies, I completed my M.A.Sc. in Information Technology at ÉTS, where my thesis investigated hyperparameter tuning for numerical solvers in rigid body simulations. I also bring industry experience as a Pipeline Developer at DNEG and a Tools Specialist at Ubisoft Montreal, where I developed, tested, and maintained production-grade software tools for visual effects and game development.
Research Interests
Reinforcement Learning
Developing deep reinforcement learning agents for sequential decision-making in complex, uncertain environments.
Operations Research
Applying mathematical optimization techniques to solve combinatorial problems. Integrating AI-driven heuristics with classical optimization methods for improved solution quality.
Physics-Based Simulation
Numerical methods for rigid body dynamics, constraint solvers, and hyperparameter optimization for interactive simulation systems used in computer graphics and VFX.
AI for Decision-Making
Designing intelligent systems that learn to make decisions under uncertainty, with applications in logistics, resource allocation, and real-time scheduling.
Publications
Hyperparameter Tuning for the Projected Gauss-Seidel Method in Rigid Body Simulations
École de technologie supérieure (ÉTS), Montreal, Canada, 2022
Proposed an automatic pipeline for tuning the hyperparameters of the projected Gauss-Seidel (PGS) iterative solver in interactive rigid body simulations.
Deep Learning Framework for Lung Cancer Tumor Segmentation from CT Scans
Mitacs Globalink Research Internship, Université de Moncton, Canada, 2019
Developed a 3D-UNet architecture for volumetric medical image analysis, achieving 92.1% sensitivity in lung cancer tumor detection from CT scans during research internship.
News
Started Ph.D. at ÉTS
Began doctoral studies in Information Technology at École de technologie supérieure, focusing on reinforcement learning and operations research.
Tools Specialist at Ubisoft Montreal
Tested and supported production pipeline tools for game development workflows.
Pipeline Technical Director at DNEG
Developed and maintained production pipelines for visual effects projects.
Completed M.A.Sc. at ÉTS
Defended thesis on hyperparameter tuning for the projected Gauss-Seidel method in rigid body simulations.
Mitacs Globalink Research Internship
Conducted deep learning research on medical image segmentation at Université de Moncton, developing 3D-UNet architectures for lung cancer detection.
Education
Ph.D. in Information Technology
École de technologie supérieure (ÉTS)Research Focus: Reinforcement Learning and Operations Research for Combinatorial Optimization
M.A.Sc. in Information Technology
École de technologie supérieure (ÉTS)Thesis: Hyperparameter tuning for the projected Gauss-Seidel method in rigid body simulations
B.Eng. in General Engineering
Tunisia Polytechnic School
Preparatory Classes (Mathematics–Physics)
Tunis Preparatory Engineering Institute (IPEIT)Professional Experience
Tools Specialist
2024 – 2025Ubisoft Montreal
Developed and maintained production pipeline tools for game development workflows. Designed automation systems and internal tools to optimize studio-wide production processes.
Pipeline Developer | ATD
2022 – 2024DNEG
Maintained and optimized production pipelines at the Academy Award-winning VFX studio. Built Python-based tooling for asset management, shot processing, and workflow automation across multiple film projects.
Mitacs Globalink Research Intern
Summer 2019Université de Moncton
Developed a deep learning framework for lung cancer tumor segmentation from CT scans. Implemented and optimized 3D-UNet architectures for volumetric medical image analysis.
Technical Expertise
Machine Learning & AI
Programming
Optimization & Math
Tools & Platforms
Selected Projects
Artificial Intelligence & Machine Learning
Medical Image Segmentation with Deep Learning
Developed a 3D-UNet framework for lung cancer tumor segmentation from CT scans during a Mitacs Globalink research internship at Université de Moncton (2019). Achieved 92.1% sensitivity in tumor detection.
Evolutionary Algorithms for Combinatorial Optimization
Implemented genetic algorithms for solving the Knapsack Problem, exploring evolutionary computation techniques including selection, crossover, and mutation operators.
Computer Graphics & Simulation
Ray Tracer from Scratch
Personal exploration of ray tracing fundamentals through a C++ implementation following Peter Shirley's Rendering series. Features CPU-based rendering with multiple material types.
Advanced Ray Tracing Renderer
CPU-based ray tracing renderer in Java with OpenGL integration. Features geometric primitive intersection, anti-aliasing, depth of field, and texture mapping.
Physics-Based Character Animation
Physics-based animation system using Proportional-Derivative (PD) controllers. Simulates a skeletal puppet suspended by virtual marionette strings in Java/OpenGL.
Finite Element Method Simulation
2D finite element method simulation for deformable bodies with implicit backward Euler time integration for numerical stability.
Embedded Systems
Smart Irrigation System
IoT-based smart irrigation system using temperature, humidity, and luminosity sensors. Implemented in C on an STM32F302R8 microcontroller.
Contact
I am always open to research collaborations, academic discussions, and opportunities. Feel free to reach out.