Marek Dědič
Machine Learning Researcher at cisco
Prague, Prague, Czechia
Summary
🤩
Rockstar🎓
Top SchoolMarek Dědič is a machine learning researcher and teaching assistant with 12 years of experience, currently pursuing a PhD in Mathematical Engineering at Czech Technical University while conducting research at Cisco on neural networks, multi-instance and graph learning. He combines academic teaching—leading tutorials and supervising theses—with industry research that applied deep learning to network security and structured data. An active open-source contributor, Marek has improved core functionality in Flux.jl and contributed TypeScript definitions to DefinitelyTyped, reflecting both backend ML tooling and frontend developer ergonomics. Beyond research, he has led a national nonprofit as executive director and volunteers as a scout educator, bringing strategic leadership and grassroots teaching experience to technical projects.
12 years of coding experience
9 years of employment as a software developer
Doctor of Philosophy - PhD, Mathematical Engineering, Doctor of Philosophy - PhD, Mathematical Engineering at Czech Technical University in PragueUniversità degli Studi di Cagliari
Czech, English, German, Italian
Github Skills (20)
javascript10
artificial-neural-networks10
typescript10
machine-learning10
typescript-definitions10
type-definition10
typedefs10
type-system10
deeplearning-ai10
dts10
deep-learning10
typescript-types10
flux10
neural-network10
fluxor10
Programming languages (21)
Github contributions (5)
DefinitelyTyped/DefinitelyTyped
May 2019 - Dec 2022
The repository for high quality TypeScript type definitions.
Role in this project:
Front-end Developer
Front-end DeveloperContributions:13 reviews, 15 commits, 39 PRs in 3 years 8 months
Contributions summary:Marek primarily contributed to the `definitelytyped/definitelytyped` repository by updating and adding TypeScript type definitions for various libraries and APIs, most notably for `google-apps-script`, `imagesloaded`, and the `wordpress` suite of tools. Their work involved modifying existing type definitions, adding new function signatures, and updating test files to ensure the type definitions accurately reflected the functionalities of the JavaScript libraries. The contributions enhanced the type safety and developer experience for users of these libraries within TypeScript projects.
typescript-definitionstype-definitionshigh-qualitydtsdefinitions
FluxML/Flux.jl
Sep 2017 - Jan 2018
Relax! Flux is the ML library that doesn't make you tensor
Role in this project:Back-end Developer & ML Engineer
Back-end Developer & ML EngineerContributions:10 commits, 5 PRs, 13 comments in 3 months
Contributions summary:Marek primarily contributed to the core functionality of the Flux.jl library, focused on improvements to the `Tracker` and `Optimise` modules. Their work involved implementing features like multi-variable `vcat` for `TrackedVector` and exposing all optimisers. Additionally, the user addressed merging and fixing code related to data handling within the library.
ml-librarythe-human-braindata-sciencedeep-learningneural-networks
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.