Max Margenot
Principal Machine Learning Engineer at Toast
Boston, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolMax Margenot is a Principal Machine Learning Engineer in Boston with 10 years of experience building production ML systems that bridge research and product. He has led ML teams across fintech, biotech, and payments—shipping causal deep learning, NLP pipelines for market signal detection, and personalized LLM fine-tuning for conversational agents at Square and Toast. A hands-on researcher and speaker, he contributes to open source work such as improving financial-analytics visualizations in the widely used alphalens library and leads fine-tuning efforts for the Goose agent. His background spans machine vision for drug-development, knowledge graphs for CRM, and creating evaluation systems for seller-facing AI, reflecting a rare blend of quantitative finance training and practical engineering. Notably, he prioritizes interpretability and accessibility in tooling, from colorblind-friendly visualizations to explainable evidence extraction for risk cases.
10 years of coding experience
11 years of employment as a software developer
Bachelor of Science (B.S.) Mathematics minor in Computer Science, Bachelor of Science (B.S.) Mathematics minor in Computer Science at University of ConnecticutMaster of Science (M.S.) Mathematical Finance, Master of Science (M.S.) Mathematical Finance at Boston University
English, Spanish
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
data-visualizations10
pandas10
data-visualization10
data-visualisation10
python10
numpy10
matplotlib10
seaborn9
finance8
algorithmic-trading8
jupyter8
Programming languages (3)
Github contributions (5)
quantopian/alphalens
Nov 2017 - Jan 2018
Performance analysis of predictive (alpha) stock factors
Role in this project:
Data Scientist
Data ScientistContributions:5 commits, 4 PRs, 6 pushes in 2 months
Contributions summary:Max primarily contributed to the visualization and analysis components of the `alphalens` library, focusing on improving the presentation and interpretability of financial data. Their work included updating plotting functions, adapting color palettes for accessibility, and ensuring consistency in the display of time series data. They modified the plotting code to incorporate moving averages, and corrected small errors in the functions. Furthermore, the user made sure the visualizations were colorblind friendly.
stock-marketalgorithmic-tradingpythonperformance-analysisnumpy
quantopian/research_public
Jun 2016 - Nov 2018
Quantitative research and educational materials
Contributions:208 commits, 174 PRs, 131 pushes in 2 years 6 months
quantitative-researchsciencebrain-computer-interfacedata-sciencescientific-computing
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.