Federico Lopez
Senior Machine Learning Engineer at Kumo
Munich, Bavaria, Germany
Summary
🤩
Rockstar🎓
Top SchoolFederico Lopez is a Senior Machine Learning Engineer and PhD candidate with 11 years of experience building production-ready deep learning systems and research-grade graph & NLP models. He has led radar perception and multi-modal temporal fusion efforts for autonomous driving at Argo AI and CARIAD, and now applies his expertise to deployable ML solutions at Kumo. His research blends non-Euclidean geometry and graph representation learning for richer text and relational embeddings, informed by a doctoral stint at HITS and a research internship at Google on hyperbolic recommender systems. Federico is a hands-on engineer who moves ideas from prototype to field operation, with notable open-source contributions to widely used NLP tooling such as Gensim and TextRank where he improved summarization, keyword extraction and robust preprocessing. Comfortable across Python and PyTorch, he combines academic rigor with pragmatic software engineering from data pipelines to deployed models. A self-described “engineer by curiosity,” he pairs mathematical fascination with practical impact in language and perception problems.
11 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD Computer Science, Doctor of Philosophy - PhD Computer Science at Heidelberg UniversitySoftware Engineering, Software Engineering at University of Buenos Aires
Spanish, English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (11)
tokenize10
gensim10
topic-modeling10
tokenizer10
nlp10
topic-models10
python10
natural-language-processing10
data-mining9
machine-learning8
word-embeddings7
Programming languages (1)
Github contributions (5)
summanlp/textrank
Sep 2014 - Apr 2018
TextRank implementation for Python 3.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:5 releases, 106 commits, 19 PRs in 3 years 7 months
Contributions summary:Federico primarily contributed to the `textrank` repository by implementing and refining text processing functionalities, specifically related to sentence splitting, stop word filtering, and lemmatization. They introduced methods for replacing abbreviations and filtering words, demonstrating a focus on data cleaning and pre-processing for NLP tasks. The commits indicate efforts to integrate these cleaning processes with the core text summarization algorithm.
nlppythonpython-3text-summarizationsummarization
piskvorky/gensim
Apr 2015 - Jul 2015
Topic Modelling for Humans
Role in this project:Data Scientist
Data ScientistContributions:8 commits, 1 PR, 6 comments in 2 months
Contributions summary:Federico implemented and refined keyword extraction and summarization functionalities within the Gensim library. They added a new summarization package and implemented a function to rank documents from a corpus. Their contributions include modifications to the keywords extraction, including the incorporation of text cleaning and graph construction for identifying key terms. Furthermore, they corrected issues related to handling documents of zero length, ensuring robustness in the summarization process.
pythonword-similarityword-embeddingsdata-miningfor-humans
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.