Brian Tung
Machine Learning Scientist at Matnex
London, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolBrian Tung is a machine learning scientist specializing in end-to-end, feedback-driven materials discovery pipelines that couple generative models, active search, and first-principles validation. With eight years of experience spanning the Max Planck Institute, the University of Cambridge, and MatNex, he has delivered rapid closed-loop outcomes—helping validate two alloys in three months—and now builds constraint-aware generative workflows refined via reinforcement learning and DFT screening. He focuses on rigorous evaluation and selection policies to make ML-driven discovery reliable in practice, and explores agentic workflows that translate high-level goals into simulation and experimental plans. His background in advanced microscopy and failure characterization informs practical validation strategies, making his models grounded in real-world material behavior. Based in London, he combines deep materials science training (PhD-level) with practical ML engineering to move candidates from proposal to experiment-ready ranking.
8 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy PhD | Dr.-Ing. Materials Science, Doctor of Philosophy PhD | Dr.-Ing. Materials Science at Ruhr University BochumDr.-Ing. Materials Science, Dr.-Ing. Materials Science at IMPRS SusMet | SurMatMaster of Science (M.Sc.) Materials Science and Engineering, Master of Science (M.Sc.) Materials Science and Engineering at National Taiwan UniversityBachelor of Science (B.Sc.) Materials Science and Engineering, Bachelor of Science (B.Sc.) Materials Science and Engineering at National Tsing Hua University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
tree-search7
biology5
benchmark4
few-shot-learning4
segmentation3
python3
machine-learning3
pytorch-lightning2
pytorch2
Programming languages (2)
Github contributions (5)
poyentung/sigma
Oct 2021 - Dec 2022
Contributions:5 releases, 226 commits, 186 pushes in 1 year 1 month
poyentung/balsa
Apr 2024 - Nov 2024
Benchmark suite tailored to evaluate various DFO algorithms for complex system optimisation.
Contributions:2 reviews, 14 PRs, 24 pushes in 7 months
benchmarkbiologyblackbox-optimizationderivative-free-optimisationmachine-learning
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.