Felice Merra
Senior Data Science Manager
Bari, Apulia, Italy
Summary
👤
Senior🎓
Top SchoolFelice Merra is a Senior Data Science Manager based in Berlin with eight years of experience building large-scale Information Retrieval, NLP, and Generative AI systems that drive measurable business impact. Currently leading Data Science at Cognism, she translates cutting-edge research—particularly in agentic workflows, multilingual models, and deep learning—into production-grade SaaS features while scaling high-performing teams across time zones. Previously she shaped search and GenAI experiences at Amazon and AWS, acting as a Science Technical Leader on Amazon Q and delivering solutions used by millions. She holds a PhD in Recommender Systems and Adversarial Machine Learning, with award-winning research that improved recommender robustness and informs her pragmatic, security-aware approach to production ML. Known for being technically hands-on and outcome-driven, she combines mentoring and strategic stakeholder alignment to consistently turn research prototypes into revenue-generating products.
9 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD Recommender Systems and Adversarial Machine Learning, Doctor of Philosophy - PhD Recommender Systems and Adversarial Machine Learning at Politecnico di Bari
Github Skills (26)
adversarial-attacks10
feature-extraction10
machine-learning10
generative-adversarial-network10
security10
keras10
matrix-factorization10
content-based-recommendation10
adversarial-machine-learning10
collaborative-filtering10
deep-learning10
knowledge-graph10
ai10
personalization10
recommender-system10
Programming languages (3)
Github contributions (5)
merrafelice/merrafelice.github.io
Aug 2019 - Jul 2022
A jekyll based resume template
Contributions:158 commits, 173 pushes, 2 branches in 3 years
jekyll
sisinflab/adversarial-recommender-systems-survey
Apr 2020 - Mar 2021
The goal of this survey is two-fold: (i) to present recent advances on adversarial machine learning (AML) for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs) for generative applications, thanks to their ability for learning (high-dimensional) data distributions. In this survey, we provide an exhaustive literature review of 74 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS or on generative models using GANs to improve their quality.
Contributions:1 review, 50 commits, 2 PRs in 10 months
adversarial-machine-learninggenerative-adversarial-networkgenerative-modelmachine-learningsecurity
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.