# Aleksa Marusic Aleksa Marusic is a remote worker on Himalayas, Data Scientist at Alstom, based in France. Source: https://himalayas.app/@aleksamarusic ```text AI/ML engineer at Alstom who delivered an engineering-drawing vision system in 8 weeks. ``` | Detail | Value | | --- | --- | | Availability | Looking for a job | | Location | France | | Authorized to work in | France | | Salary expectations | 90k+ EUR | | Job categories | AI ML Engineer, Data Scientist, Research Scientist, Computer Vision Engineer, Robotics Engineer | | Skills | Computer Vision, Vision Language Models, Deep Learning, Transformers, Robot Control, Imitation Learning, Reinforcement Learning, Anomaly Detection, Pose Estimation, Optical Character Recognition, Natural Language Processing, Humanoid Robotics, Balance, Time Series Analysis, 3D Reconstruction | | LinkedIn | https://linkedin.com/in/aleksamarusic | | GitHub | https://github.com/aleksamarusic | ## About ```text At Alstom, I designed a computer-vision solution for legacy engineering drawings that reached 89% detection and 85% classification accuracy in 8 weeks, using each drawing’s legend as guidance. I also led model analysis for predictive-maintenance anomaly detection, where the design outperformed the baseline. At Institut Polytechnique de Paris, I researched human-motion analysis for physical rehabilitation, including robot control in simulation and on hardware. My PhysioFormer work set new state-of-the-art results on the KIMORE, UI-PRMD and KERAAL benchmarks; another framework advanced error classification and localization on KERAAL. Earlier, I developed engineering-drawing algorithms at Spare Parts 3D and worked on C++ graphics drivers at NVIDIA. I’m completing a PhD in Deep Learning for Robotics, with my defence expected in December 2026, and have four first-author peer-reviewed publications. ``` ## Experience ### Data Scientist (current) [Alstom](https://himalayas.app/companies/alstom). Sep 2025 - Present ```text Lead engineer for computer vision on legacy engineering drawings, achieving 89% detection and 85% classification accuracy in 8 weeks. Also led time-series anomaly detection for predictive maintenance, outperforming baseline. ``` Skills: Computer-Vision, OpenCV, Vision-Language-Models, Time-Series-Analysis, Anomaly-Detection, Predictive-Maintenance ### PhD Researcher Institut Polytechnique de Paris. Dec 2021 - Dec 2025 ```text Conducted research on human motion analysis for physical rehabilitation, including robot control and imitation learning on a humanoid robot. Developed PhysioFormer, achieving state-of-the-art results on rehabilitation benchmarks. ``` Skills: Deep-Learning, Transformers, Computer-Vision, Robot-Control, Imitation-Learning, ROS, Human-Motion-Analysis ### Teaching Assistant, Machine Learning École Polytechnique. Sep 2021 - Sep 2024 ```text Advised, evaluated, and taught students in laboratory sessions for CSE204 and CSE201. ``` Skills: Machine-Learning, Teaching, Mentorship ### Machine Learning Research Intern Spare Parts 3D. Mar 2021 - Sep 2021 ```text Developed algorithms to extract information from 2D engineering drawings, including projection views, OCR, and dimension extraction. Rebuilt 3D models from projection views for 3D printing. ``` Skills: Python, C++, OpenCV, OCR, 3D-Modeling, FreeCAD, STL ### Machine Learning Engineer mBrainTrain. Apr 2020 - Jun 2020 ```text Applied deep learning to EEG brain signals for actionable predictions. ``` Skills: Deep-Learning, EEG, Signal-Processing ### Software Engineering Intern [NVIDIA](https://himalayas.app/companies/nvidia). Jul 2019 - Dec 2019 ```text Worked on C++ graphics drivers, focusing on power optimization for integrated/dedicated GPU transitions. ``` Skills: C++, Graphics-Drivers, Power-Optimization ## Education ### Institut Polytechnique de Paris PhD, Deep Learning for Robotics. 2021 - Present ```text PhD in Deep Learning for Robotics, with thesis on deep learning based analysis and assessment of human motion for physical rehabilitation. Defence expected December 2026. ``` ### Institut Polytechnique de Paris Master of Science, Data and Artificial Intelligence. 2020 - 2021 ```text MSc in Data and Artificial Intelligence, graduated with honors. ``` ### University of Belgrade Bachelor of Science, Software Engineering. 2015 - 2020. Grade: 9.0/10 ```text BSc in Software Engineering with a GPA of 9.0 out of 10. ``` ### Mathematical Grammar School Belgrade High School Diploma, Mathematics, Physics, and Computer Science. 2009 - 2015 ```text Specialised school for mathematics, physics and computer science; students regularly win international Olympiad medals. ``` ## Tech stack - OpenCV - Python - C++ - C - TensorFlow - PyTorch - scikit-learn - Keras - Transformers - Linux - Git - Docker - SQL To contact Aleksa, message them from this profile with a Himalayas employer account: [Hire on Himalayas](https://himalayas.app/hire). ## People also viewed - [Krissaan Amen Allah](https://himalayas.app/@krissaanamenallah): Research Internship AI Engineer, STMicroelectronics - [Paul Chauvin](https://himalayas.app/@paulchauvin): Machine Learning Engineer, Freelance - [rahma melki](https://himalayas.app/@rahmamelki): Researcher, Medical Imaging, Pascal Institute - [Clément Morin](https://himalayas.app/@clmentmorin): AI engineer, Iglobescientific - [Promise Adiole](https://himalayas.app/@promiseadiole): AI & Robotics Research Intern, Cyber Physical Systems Group - [Nassim User](https://himalayas.app/@nassimuser): Research Intern: 3D Medical Image Translation, BioMaps, CEA & Université Paris Saclay - [Sébastien Combrexelle](https://himalayas.app/@sbastiencombrexelle): 3D Machine Learning Engineer, Squaremind - [Hassna EL-BOUSIYDY](https://himalayas.app/@hassnael-bousiydy): Machine Learning & NLP Engineer | PhD Candidate, LRCS Laboratoire de Réactivité et Chimie des Solides - [ilyes sais](https://himalayas.app/@ilyessais): Research Intern Embedded AI & Multi Robot Autonomy, Thales cortAIx - [Chelsy Mena](https://himalayas.app/@chelsymena): Machine Learning Research Intern, Inria / Universite Paris Saclay