André Panisson
Principal Researcher at Intesa Sanpaolo
Turin, Piedmont, Italy
Summary
👤
Senior🎓
Top SchoolAndré Panisson is a Principal Researcher and team lead based in Turin with 16+ years building trustworthy, human-centric AI that bridges machine learning, network science, and data engineering. He designs and operationalizes explainability, fairness, and transparency pipelines—translating research into regulated, high-stakes deployments in finance, healthcare, and legal domains. He leads EU-funded trials (PRE-ACT) and industrial collaborations that apply GNNs, RAG/LLMs, and bias-aware evaluation to real-world decision processes such as breast radiotherapy and anti-financial-crime systems. His background spans foundational publications (NeurIPS, KDD, TMLR) and production engineering—from real-time sensor systems to scalable graph-based risk detection—reflecting both academic depth and delivery focus. An early open-source contributor, he has hands-on experience improving Twitter’s Elephant Bird loader to handle nested JSON in large Hadoop pipelines, a detail that highlights his long-standing blend of systems work and data science. Fluent across academic and industrial ecosystems, he mentors teams to move explainable ML from prototype to accountable production.
16 years of coding experience
23 years of employment as a software developer
Doctor of Philosophy, Computer Science, Doctor of Philosophy, Computer Science at University of TurinMaster of Science, Computer Science, Master of Science, Computer Science at Federal University of Rio Grande do Sul
Portuguese, Italian, English
Stackoverflow
876reputation
49kreached
11answers
5questions
Github Skills (19)
json-parser10
json10
jsonp10
hadoop10
java10
javas10
parsing10
apache-pig9
unit-testing9
macos6
keras6
toolkits6
gephi6
graphml6
tensorflow6
Programming languages (7)
Github contributions (5)
twitter/elephant-bird
Mar 2012 - Apr 2012
Twitter's collection of LZO and Protocol Buffer-related Hadoop, Pig, Hive, and HBase code.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:11 commits in 10 days
Contributions summary:André primarily contributed to the `JsonLoader` class, which is part of a larger Hadoop ecosystem, by adding functionality to handle nested JSON structures. They implemented features that allowed nested JSON objects to be loaded as nested Maps and JSON arrays as Bags within the Pig data model. The user also added options to control backwards compatibility and loading behavior, and created corresponding unit tests to ensure proper handling of nested structures and backward compatibility. Furthermore, they refactored the loader to remove specific fields specification feature and added constructor options.
pigssreflectflink-sqlbuffertla
panisson/panisson.github.io
Jan 2015 - Jul 2024
Contributions:12 pushes in 9 years 7 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.