Machine Learning Engineer focused on multimodal ML, geospatial AI, and applied AI systems.
MSc Electrical & Computer Engineering @ University of Alberta.
I build machine learning systems that connect real-world data, model adaptation, and practical engineering workflows — from multi-sensor satellite methane detection to browser-based AI automation and scientific simulation systems.
Open to: Machine Learning Engineer · Applied AI Engineer · Computer Vision · Software Engineer, ML Systems
Quick links:
Email · LinkedIn · GitHub
My interests lie at the intersection of machine learning, computer vision, geospatial / remote sensing data engineering, and applied AI systems.
Across my projects, I often work with real-world constraints such as incomplete observations, cross-domain mismatch, noisy labels, limited data availability, and deployment-oriented engineering trade-offs. I am especially interested in building ML systems that are not only accurate in controlled settings, but also practical under real data and workflow constraints.
Current areas I am exploring include:
- Multimodal ML with incomplete or heterogeneous real-world data
- Vision Transformer-based modeling, adaptation, and evaluation
- LLM agents, tool-calling workflows, and applied AI automation
- Data engineering pipelines for ML experiments and reproducible evaluation
- Performance-aware implementation with Python, C++, and distributed / HPC workflows
I am interested in applied AI systems, computer vision, geospatial AI, and research-to-product ML workflows.
Feel free to reach out through LinkedIn or email me at yuyaow42@gmail.com.