Henry Kenlay
Member Of Technical Staff at Latent Labs
London, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolHenry Kenlay is a member of technical staff at Latent Labs with nine years of experience applying machine learning to molecular and biological problems, most recently building frontier models for all molecules of life. He previously drove antibody design ML as an immunoinformatics research scientist at Exscientia and completed a DPhil at Oxford studying robustness in graph machine learning and spectral filters. His background spans computational biology, deep learning for genomics and epigenetics, and practical software engineering from internships to production code. Henry is an active contributor to adversarial robustness tooling—having improved PGD and IG attacks in the deeprobust PyTorch library—demonstrating both research depth and engineering polish. He pairs rigorous mathematical training (Discrete Mathematics BSc, top of class) with hands-on experience across academia and industry, and often translates complex models into reproducible code. Colleagues value his ability to bridge theoretical robustness insights with applied molecular ML development.
9 years of coding experience
2 years of employment as a software developer
DPhil, CDT Autonomous Intelligent Machines & Systems, DPhil, CDT Autonomous Intelligent Machines & Systems at University of OxfordComputational Biology (MPhil), Computational Biology, Computational Biology (MPhil), Computational Biology at University of CambridgeCaroline Chisholm schoolDiscrete Mathematics BSc, Computer Science, First class (ranked 2nd), Discrete Mathematics BSc, Computer Science, First class (ranked 2nd) at University of Warwick
English
Github Skills (8)
pytorch10
machine-learning10
adversarial-attacks10
deep-learning10
graph-neural-network10
python10
sparse9
numpy8
Programming languages (4)
Github contributions (5)
DSE-MSU/DeepRobust
Jun 2020 - Jun 2020
A pytorch adversarial library for attack and defense methods on images and graphs
Role in this project:
ML Engineer
ML EngineerContributions:9 commits, 5 PRs, 2 comments in 13 days
Contributions summary:Henry primarily contributed to the `deeprobust` repository, which focuses on adversarial attacks and defenses in the context of graph neural networks. Their commits involved modifying and enhancing the `PGDAttack` and `IGAttack` methods within the global attack module. They added new parameters like 'epochs' to the PGD attack and refactored code for better consistency. Furthermore, the user refactored and improved import statements and adjusted variable names to enhance code clarity.
pytorchadversarial-attacksgraph-convolutional-networksdeep-learningadversarial
henrykenlay/grapht
Jan 2020 - Jul 2020
Contributions:7 PRs, 124 pushes, 9 branches in 6 months
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.