Luyolo Magangane
About Luyolo Magangane
Luyolo Magangane is a Senior Machine Learning Engineer at Delivery Hero in Berlin, Germany, with extensive experience in machine learning and data science roles across various companies in South Africa.
Current Position at Delivery Hero
Luyolo Magangane currently holds the position of Senior Machine Learning Engineer at Delivery Hero in Berlin, Germany. He began his tenure at Delivery Hero on November 1, 2022. In this role, he focuses on advanced machine learning projects, contributing to the company's technical and operational frameworks.
Previous Role at DataProphet
In 2022, Luyolo Magangane worked briefly for four months at DataProphet as a Senior Machine Learning Engineer in Cape Town, Western Cape, South Africa. During this time, he engaged in high-level machine learning tasks and collaborated on predictive modeling and optimization solutions for various industry needs.
Tenure at Amazon
From 2019 to 2021, Luyolo Magangane was employed at Amazon in Cape Town Area, South Africa, as an Applied Scientist. This role saw him delve into integrating machine learning solutions into Amazon's vast ecosystem, contributing to the advancement of its digital and operational capacities.
Educational Background
Luyolo Magangane has a strong academic background in engineering and applied mathematics. He achieved a Master of Science (MS) in Applied Mathematics from Stellenbosch University from 2018 to 2020. Prior to this, he earned a Bachelor of Engineering (B.Eng.) in Electrical and Computer Engineering from the University of Cape Town, where he studied from 2007 to 2010. He completed his secondary education at Veritas College Senior School, attending from 2002 to 2006.
Expertise in Machine Learning and Data Science
Throughout his career, Luyolo Magangane has specialized in open-domain concept modeling using knowledge graphs and statistical relational learning. His expertise extends to latent feature and multi-hop graph modeling within the domain of graphical machine learning. Additionally, he focuses on knowledge-intensive language task modeling, including natural language dialogue, complex question answering, and entity-relational link prediction.