Simon Graham
Co-Founder And Chief Technology Officer at University of Warwick
United Kingdom
Summary
👤
Senior🎓
Top SchoolSimon Graham is a Co-Founder and CTO at Histofy with a decade of experience translating deep learning research into deployable pathology solutions. He completed a prize-winning PhD on "Localisation and Symmetry in Computational Pathology" after earning a First Class Honours in Mathematics, and now blends academic rigor with product-focused MLOps and backend engineering. His open-source contributions include practical enhancements to the well-known Hover-Net nuclear segmentation repo, reflecting hands-on work in model architecture, data loading and inference pipelines. Previously an Assistant Professor and Honorary Fellow at the University of Warwick, he has a track record of moving algorithms from lab prototypes to clinical-grade tooling. Colleagues describe him as a pragmatic researcher-founder who pairs mathematical depth with production engineering discipline.
9 years of coding experience
5 years of employment as a software developer
BSc Mathematics, BSc Mathematics at Loughborough UniversityThe Sixth Form College SolihullPhD- Localisation and Symmetry in Computational Pathology Mathematics and Computer Science, PhD- Localisation and Symmetry in Computational Pathology Mathematics and Computer Science at University of Warwick
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
computer-vision10
trainings10
python10
modeling10
data-processing9
tensorflow9
machine-learning9
continuous-deployment8
ml-deployment8
Programming languages (2)
Github contributions (5)
vqdang/hover_net
Jan 2019 - Dec 2021
Simultaneous Nuclear Instance Segmentation and Classification in H&E Histology Images.
Role in this project:
Back-end Developer & MLOps Engineer
Back-end Developer & MLOps EngineerContributions:1 review, 154 commits, 6 PRs in 3 years
Contributions summary:Simon made small modifications to the code, particularly in the graph, metrics, and train files. These changes included adjustments to model components and loss functions. There are also changes related to inference, data loading and patch extraction suggesting the user was focused on model training and deployment pipeline. This indicates a focus on model architecture and data processing for the project.
segmentationdeep-learningcomputer-visionsimultaneoushistology
simongraham/hovernet_inference
Nov 2019 - Oct 2021
HoVer-Net inference code for simultaneous nuclear segmentation and classification
Contributions:102 commits, 6 PRs, 25 pushes in 1 year 11 months
pytorchsegmentationdeep-learninginferencehover
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.