Advance composite structures research with machine learning and finite element analysis in a limited hybrid Aerospace work arrangement. The National Research Council’s two-year Postdoctoral Fellow project develops a Physics-Informed Mesh Graph Networks solver. The work integrates deep learning with governing physics for composite airframe Certification-by-Analysis. You will study damage mechanisms, prediction accuracy, and quantified reliability through computational mechanics. Key Responsibilities: Develop a Physics-Informed Mesh Graph Networks solver Integrate deep learning with governing composite-structure physics Model composite airframe damage mechanisms using computational methods Support productive,



reliable Certification-by-Analysis of structures Work under direct supervision in an NRC research laboratory Requirements: PhD in mechanical, civil, or aerospace engineering Focus on computational mechanics of composite structures Experience modelling composite damage with finite elements Experience with Abaqus user-subroutine development and coding Understanding of machine learning for engineering problems Apply machine learning, Abaqus, and computational mechanics to composite airframe analysis as an NRC postdoctoral researcher. #J-18808-Ljbffr

📌 Composite Structures Machine Learning Fellow (Ottawa)
🏢 National Research Council of Canada
📍 Ottawa