Fande Kong
Applied Scientist at Amazon
Greater Seattle Area United States
Summary
🤩
Rockstar🎓
Top SchoolFande Kong is an Applied Scientist with 11 years of experience bridging high-performance scientific computing and production machine learning, now leading AI-powered search and recommendation work at Amazon. He has a rare combination of deep numerical methods expertise—authoring PETSc-related contributions and the MOOSE framework used globally—and practical ML at scale, building transformer-based ranking models and ad recommendation systems serving millions. Fande’s background in accelerating multiphysics simulations on 40K+ cores informs his systems-first approach to distributed model deployment and real-time data pipelines. He holds a PhD-level research pedigree from the University of Colorado Boulder and a track record of shipping both open-source scientific software and production ML systems. Notably, his open-source contributions to libMesh/PETSc SLEPc integrations reflect an ability to improve foundational solver APIs as well as end-user machine learning experiences.
11 years of coding experience
13 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Computer Science, Doctor of Philosophy (Ph.D.) Computer Science at University of Colorado Boulder
English, Chinese
Github Skills (8)
petsc10
sparse-matrix10
eigenvector10
parallel-computing10
eigenvalue10
finite-element-analysis9
c-language8
cprogramming-language8
Programming languages (8)
Github contributions (5)
libMesh/libmesh
Sep 2016 - Jan 2022
libMesh github repository
Role in this project:
Back-end Developer
Back-end DeveloperContributions:41 reviews, 51 commits, 37 PRs in 5 years 5 months
Contributions summary:Fande primarily focused on enhancing the `libMesh` repository by introducing new features and improving existing functionalities related to the SLEPc and PETSc solvers. Their contributions included declaring and implementing a `TransientEigenSystem`, adding API functionality for sparse matrix management with flush operations, and introducing flags for closing matrices before solving. They also worked on assigning node processor IDs and optimized node assignment algorithms.
golangfinite-element-analysisfemparallelfinite-element-methods
fdkong/libmesh
Sep 2016 - Apr 2022
libMesh github repository
Contributions:81 pushes, 39 branches in 5 years 7 months
golangtrellisnetbox
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.