Simon Thomas

Associate In Model Risk Management (ML Quantitative Researcher)

London, England, United Kingdom
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts
email-iconphone-icongithub-logolinkedin-logotwitter-logostackoverflow-logofacebook-logo
Join Prog.AI to see contacts

Summary

👤
Senior
🎓
Top School
Simon Thomas is an ML-focused quantitative researcher and Associate in Model Risk Management at Goldman Sachs, bringing eight years of research and applied experience at the intersection of thermodynamics, extreme value theory and machine learning. He recently completed a PhD at Cambridge studying storm surge and tropical cyclone extremes, and has translated that domain expertise into validating and benchmarking AI/ML models for high-stakes financial workflows. His background spans hands-on deep-learning downscaling for RMS, probabilistic ML and Gaussian processes for sea-surface height analysis, and developing multi-agent automation for model validation. Comfortable with large geophysical datasets and uncertainty quantification, he combines rigorous academic training with practical model-risk engineering in London. An unexpected strength is his track record of turning physically motivated numerical models into cheaply approximated ML surrogates while probing their behaviour at extremes.
code8 years of coding experience
job1 year of employment as a software developer
bookFettes College
bookDoctor of Philosophy - PhD Department of Applied Mathematics and Theoretical Physics, Doctor of Philosophy - PhD Department of Applied Mathematics and Theoretical Physics at University of Cambridge
stackoverflow-logo

Stackoverflow

Stats
1reputation
0reached
0answers
0questions
github-logo-circle

Github Skills (60)

fragmentation10
forge10
biodiversity10
biodiversity-informatics9
ecology9
trend9
conda9
survey9
python8
gis8
landscape8
typescript8
graph8
geospatial8
netcdf8

Programming languages (6)

TypeScriptShellHTMLJupyter NotebookPythonKotlin

Github contributions (5)

github-logo-circle
so-wise/so-fronts

Apr 2021 - Nov 2021

Contributions:4 releases, 275 commits, 58 pushes in 6 months
sdat2/seager19

Nov 2020 - Oct 2022

Replication of Seager et al. (2019) Nat. Clim. Chan. They used a simple-as-possible coupled model to explain the bias in the nino3.4 trend in climate models (CMIP5). This repository replicates/reproduces their work, shows that it also applies to CMIP6, and varies some of the parameters.
Contributions:1 release, 969 commits, 43 PRs in 1 year 11 months
climateclimate-modelsocean-sciencesatmosphere-modelparameters
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.
Request Free Trial