About the Author
I am a Principal Machine Learning Engineer with 10+ years designing, building, and operating production-grade ML systems across energy, industrial, and semiconductor domains. My work spans the full arc of a machine learning project: framing the problem, building the model, engineering the pipeline, and keeping it honest in production.
At Analog Devices, I architect machine learning systems for supply chain demand planning and edge inference. Previously at Eaton, I served as Lead Data Scientist and Principal Investigator at the Centre for Intelligent Power, securing €1.6M in competitive research funding and receiving the Eaton STAR Leadership Award for engineering innovation and cross-functional impact. My open-source work includes Twiga, a production forecasting library with REST serving and MLOps integration, MLPForecast, an MLP-based net-load forecasting toolkit with uncertainty quantification, and Deep-NILMtk, a community deep learning toolkit for non-intrusive load monitoring.
Projects → sambaiga.github.io/pages/projects
My research spans non-intrusive load monitoring, probabilistic forecasting, uncertainty quantification, physics-based intelligence, and AI for reliability engineering. I have authored 10+ peer-reviewed papers in IEEE Transactions on Smart Grid, IEEE Transactions on Power Systems, and IEEE Transactions on Industrial Informatics.
Publications → sambaiga.github.io/pages/publication · ORCID
I also write about machine learning, Bayesian thinking, and applied AI at: