Ashish Dhiman
About Ashish Dhiman
Ashish Dhiman is an Expert Machine Learning Engineer at TomTom, with extensive experience in machine learning and data science across various companies and projects.
Current Position at TomTom
Ashish Dhiman currently works at TomTom as an Expert Machine Learning Engineer. He has been with TomTom since 2022, contributing to their ongoing projects from Ghent, Flemish Region, Belgium. His role involves working on advanced machine learning and data science projects relevant to digital mapping and in-car navigation services.
Previous Roles at TomTom
Before becoming an Expert Machine Learning Engineer, Ashish Dhiman worked at TomTom as a Senior Machine Learning Engineer from 2020 to 2022 in the Gent area, Belgium. In this role, he was responsible for developing a pipeline for normalizing, de-duplicating, and conflating place data using semantic text-matching and TF-IDF methodologies, and implementing advanced features for digital mapping services.
Experience at HERE Technologies
Ashish Dhiman was employed at HERE Technologies between 2016 and 2020. Initially, he served as a Machine Learning Engineer from 2016 to 2018, and then as a Senior Data Scientist from 2018 to 2020 in Mumbai, Maharashtra, India. His contributions included developing processes for removing building and forest heights from digital elevation models and designing algorithms for data size reduction in in-car maps.
Education and Academic Background
Ashish Dhiman pursued a Master of Computer Science with a focus on Machine Learning at the Georgia Institute of Technology from 2020 to 2023. Prior to that, he completed a Bachelor of Technology (B.Tech.) in Electrical and Electronics Engineering at the National Institute of Technology Hamirpur from 2008 to 2012.
Notable Projects and Contributions
Ashish Dhiman leads the technical development of a European Commission-funded research project dedicated to extracting and monitoring land cover features from temporal satellite imagery. He has delivered research papers and code that have reduced project costs by 30%. He also designed a road network comparison process using Graph Neural Networks (GNN) embeddings and created a warning system for identifying graffiti vandalism using contrastive learning techniques.