Jules Udahemuka

AI Researcher/Engineer - Climate & SciML

Twitter LinkedIn GitHub

I’m Jules, a recent graduate of Carnegie Mellon University’s Master of Science in Engineering Artificial Intelligence, where I specialized in applying AI and Scientific Machine Learning (SciML) to address critical challenges in climate science.

My academic work is built on a strong foundation of professional experience as a Data Scientist and BI & Analytics Engineer. I have a track record of translating complex data into actionable insights, building everything from ML-driven revenue optimizations to robust data warehouses and impactful dashboards.

I am passionate about the entire data lifecycle—from research and modeling to engineering and deployment. I am currently seeking a role where I can leverage my skills in AI/ML and analytics to build reliable and impactful solutions.

Interests

  • Machine Learning; SciML, and Computer Vision
  • Climate Science, and Weather Prediction
  • Foundation Research
  • Open Science

Education

  • 🎓 MSc in Artificial Intelligence, 2023 - 2025
    Carnegie Mellon University
  • 🎓 BSc in Environmental Engineering, 2013 - 2017
    University of Rwanda

Skills

GitHub Activity

GitHub Commit Calendar

Research & Projects

Nucleate Winner

Founder of MonitorMed AI: 1st Place at Nucleate Bio-Hack

Won the $1,500 Patient Safety Technology Challenge by developing MonitorMed AI, a platform that quantifies uncertainty in medical imaging models using Monte Carlo dropout. Now building an "Evaluation Store" to monitor data quality, model drift, and performance as part of the Nucleate Activator program.

Climate AI Project

Climate AI: Winner of the NextGen Space Challenge

Selected as a winner in the international NextGen Space Challenge for Climate AI. This work, recognized by a panel including the UK and African Space Agencies, enhances the ClimODE framework by downscaling climate models for precise, regional predictions in Rwanda.

Neural ODEs

Neural ODEs for Regional Weather and Climate Prediction (Ongoing Research)

Developing a novel approach for downscaling global climate predictions using Neural ODEs. Leveraged domain-specific datasets and scalable architectures to enhance predictive accuracy for developing regions.

Computer Vision Project

Drones Computer Vision

Developed an open-source project for analyzing drone footage and applying computer vision techniques like YOLO and Faster R-CNN for real-time object detection and tracking.

AI Power Demand Paper

The Growing Appetite: Artificial Intelligence's Impact on Electric Power Demand and Climate Implications

A research paper exploring the escalating electrical power consumption of AI, its environmental consequences, and potential mitigation strategies. This paper provides a comprehensive analysis of the technical drivers of AI's energy demand, its impact on power infrastructure, and the associated climate implications.

Paper Implementation, The ResNet Paper

Image Classification & Verification Using Improved ResNets(with SE, Attention Layer)

Implemented ResNet paper and improved it with SE and Transform layers for image classification and face verification, achieving a classification accuracy of 90%+ in both tasks.

Digital Twin

Digital Twin for Climate Change

Created a digital twin framework using AI and simulation to model and visualize the potential impacts of climate change on the African continent.

USSD Security Paper

Enhancing Security in USSD-based Financial Systems: A Comprehensive Approach Leveraging Machine Learning, and Intelligent Agents.

A research project that develops a comprehensive framework to enhance the security of USSD-based financial systems against social engineering attacks and fraudulent activities. The framework leverages an ensemble of machine learning models and intelligent agents to provide a robust, adaptive, and interpretable solution.

Atmospheric Circulation Paper

Atmospheric Circulation and Rainfall Patterns: Bridging Climate Science Fundamentals with Advanced Modeling Techniques

A review paper that provides a comprehensive overview of the fundamental principles governing atmospheric circulation and rainfall patterns, while also exploring the cutting-edge modeling approaches that promise to enhance our predictive capabilities.

Now Reading

Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions

Paul Pu Liang, Amir Zadeh, Louis-Philippe Morency. 2022.

Speech and Language Processing

Dan Jurafsky and James H. Martin. 2024.

Attention Is All You Need

Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin. 2017.

An Introduction to Variational Inference