Sandro Hanea
Senior Software Engineer at Microsoft
Barcelona, Catalonia, Spain
Summary
🤩
Rockstar🎓
Top SchoolSandro Hanea is a Senior Software Engineer based in Barcelona with 7 years of experience building production-grade .NET systems and AI tooling. Currently on Microsoft’s AI and Search Platform, he helps ground copilots and agents with up-to-date knowledge, and previously contributed to media and messaging features for Teams, improving video, image processing and observability. An active open-source contributor, Sandro has made notable cross-cutting contributions to whisper.cpp and maintains whisper.net, bridging native C++ audio/ML work with .NET speech-to-text APIs. He combines back-end engineering, front-end UI work (Material Design for Blazor), and practical ML engineering—often implementing nuanced features like phase vocoder support, OpenVINO initialization, and language autodetection. His background as a founder/CEO and formal CS training gives him a pragmatic, product-oriented approach to technical problems.
7 years of coding experience
9 years of employment as a software developer
Information Technology, Information Technology at Colegiul National Gheorghe Lazar SibiuBachelor's degree Computer Science, Bachelor's degree Computer Science at Babes-Bolyai University
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (26)
speech-to-text10
c-language10
translation10
marshalling10
net10
razor-components10
dotnet10
inference10
blazor10
asp-net10
material-design10
gm10
front-end-development10
dotnet-core10
transformer10
Programming languages (9)
Github contributions (5)
sandrohanea/whisper.net
Feb 2023 - Mar 2023
Whisper.net. Speech to text made simple using Whisper Models
Role in this project:
Back-end Developer
Back-end DeveloperContributions:16 releases, 22 reviews, 14 commits in 1 month
Contributions summary:Sandro made significant contributions to the `Whisper.net` project, focused on implementing core functionalities for speech-to-text processing. They added features such as exposing the WaveParser and incorporating C++ native debugging. Furthermore, the user implemented an auto-detection of language feature, which is a core requirement for the project. They also refactored the builder and updated the Whisper core, adding more control on processing with multiple features such as temperature or context size.
cross-platformdotnetdotnetcorespeech-recognitionspeech-to-text
ggerganov/whisper.cpp
Feb 2023 - Mar 2025
Port of OpenAI's Whisper model in C/C++
Role in this project:ML Engineer
ML EngineerContributions:9 reviews, 12 PRs, 34 comments in 2 years 2 months
Contributions summary:Sandro contributed to the core functionality of the whisper.cpp project, focusing on improving the underlying models and their integration. They worked on implementing features related to the phase vocoder, and adding the state parameter and associated methods to the context, enhancing the overall usability. The contributions also involve fixes and improvements to the processing methods, along with the addition of functionality for initializing and using OpenVINO, and implementing a method to extract the "no speech" probability from the state.
cppwhisperspeech-to-textinferencespeech-recognition
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.