Marcelo Sardelich
Systematic Commodities
Stony Stratford, England, United Kingdom
Summary
👤
Senior🎓
Top SchoolMarcelo Sardelich is a quantitative trading and ML specialist with 12 years of experience building systematic strategies across commodities and corporate trading desks. He combines a PhD-level computer science background with hands-on roles from proprietary trading at BBVA to leading quant desks at Votorantim and Anglo American, and now works on systematic commodities at LMR Partners. His expertise spans quantitative portfolio management, linear and stochastic optimization, and sequential learning including deep reinforcement learning applied to time-series. He also applies NLP and multimodal deep learning to extract signals from unstructured data, bridging classical mathematical finance with modern ML. Notably, he has run both research-heavy and production-focused teams—including a stint as Chief Data Science Officer—so he understands model lifecycle, risk constraints, and deployable systems. Based in Stony Stratford, UK, he brings a rare mix of physics, trading intuition, and algorithmic engineering to commodity markets.
12 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy (PhD), Computer Science, Doctor of Philosophy (PhD), Computer Science at University of YorkMaster of Science (MSc), Physics, Master of Science (MSc), Physics at Universidade de São Paulo / USP
English, Portuguese, Spanish
Stackoverflow
972reputation
69kreached
4answers
12questions
Github Skills (63)
word2vec9
community-detection9
fasttext9
gensim9
topic-modeling9
partitions9
nlp8
approximation8
sketchup8
glove8
factorization8
corpus8
word-embeddings8
latent-dirichlet-allocation8
sympy7
Programming languages (2)
Github contributions (5)
MSardelich/CJay
Jun 2014 - Jul 2014
Contributions:93 commits in 23 days
MSardelich/Cluster_Ensembles
May 2016 - Sep 2016
Contributions:2 pushes in 4 months
consensus-clusteringconsolidatedconsensusoptimization-problemoptimization
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.