Summary
Peder Aursand is a manager and full-stack subsurface data scientist with a decade of experience building and operationalizing machine learning systems for the energy sector. He leads interdisciplinary teams at Aker BP to deploy daily-used ML models, implement MLOps on cloud-native platforms like GCP/Kubernetes and Kubeflow, and mature internal data-science capabilities. His background combines a PhD in Applied Mathematics and an MSc in Applied Physics and Mathematics with hands-on engineering across Python, cloud (GCP/AWS), and scientific computing stacks. Peder’s work spans automatic interpretation of seismic and subsurface data, production model hosting and serving, and pragmatic digitalization and stakeholder alignment. He brings rare depth in numerical modeling and scientific software from earlier research roles (Fortran, OpenFOAM, finite-volume/DG methods) that informs robust, physics-aware ML solutions. Based in Oslo, he pairs strong academic rigor with a demonstrated track record of shipping production-ready AI in complex, safety-critical environments.
10 years of coding experience
12 years of employment as a software developer
Exchange semester Applied physics and mathematics, Exchange semester Applied physics and mathematics at University of Glasgow
Applied Mathematics, Applied Mathematics at ETH Zürich
Norwegian University of Science and Technology
English, German, Norwegian