Ebrahim Soroush
Technical Lead at Raisin
Frankfurt, Hesse, Germany
Summary
👤
Senior🎓
Top SchoolEbrahim Soroush is a Technical Lead based in Frankfurt with 10 years of experience building production-ready ML and data systems, specializing in Python, SQL, shell scripting, NLP and computer vision. He has led end-to-end projects from streaming pipelines and Kubernetes orchestration to regulatory reporting automation, and recently architected a Ray.io + Redis Streams pipeline processing over a million articles per day. Comfortable bridging ML research and production, he has implemented LLM and deep-learning pipelines as well as graph-based knowledge extraction for real-world use cases. An active open-source contributor, he added a SpaCy interface and span-based entity support to the DyGIE++ repo, making advanced relation and event extraction easier to integrate. With an MS in Digital Electronics, Ebrahim combines strong engineering discipline with practical DevOps/MLOps know-how to deliver scalable, auditable systems.
10 years of coding experience
9 years of employment as a software developer
Amirkabir University of Technology
English, Persian, German
Github Skills (11)
named-entity-extraction10
machine-learning10
nlp10
named-entity-recognition10
entity-extraction10
spacy10
relation-extraction10
python10
natural-language-processing10
ml10
allennlp9
Programming languages (9)
Github contributions (5)
dwadden/dygiepp
Nov 2021 - Mar 2022
Span-based system for named entity, relation, and event extraction.
Role in this project:
ML Engineer
ML EngineerContributions:6 commits, 4 PRs, 17 comments in 3 months
Contributions summary:Ebrahim contributed to the `dygiepp` repository by adding a Spacy interface for the DyGIE++ model. This involved creating a custom Spacy pipeline component to integrate the DyGIE++ model, enabling named entity recognition, relation extraction, and potentially event extraction within Spacy. The user also updated the interface to be compatible with earlier versions of Spacy and added a unit test and span-based entities.
nlpentity-relationextractionentityentity-linking
e3oroush/cs231n
Sep 2018 - Sep 2022
My Answers to Assignments of Stanford CS231n Spring 2018. Mostly PyTorch solutions.
Contributions:40 commits, 26 PRs, 33 pushes in 4 years
pytorchstanforddeep-learningstanford-cs231nspring
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.