Kinyugo Maina is a machine learning researcher with eight years of experience specializing in efficient generative models across domains from bioinformatics to music. Based in Nairobi, he builds production-ready ML systems and has taken research prototypes through to deployed features during his tenure at Pixelcut.ai. As an independent researcher he developed and open-sourced Msanii, a lightweight music synthesis model that balances audio quality with computational efficiency. His background in bioinformatics and pangenomic pipelines gives him a rare cross-disciplinary perspective that informs his approach to data and model design. Kinyugo is an active open-source advocate and communicator who shares research through code, talks, and publications. He seeks collaborations that translate generative AI advances into practical, reproducible tools.
8 years of coding experience
2 years of employment as a software developer
Bachelor's degree, Computer Science, Second Class Honours Upper Division, Bachelor's degree, Computer Science, Second Class Honours Upper Division at DEDAN KIMATHI UNIVERSITY OF TECHNOLOGY (DeKUT)
A novel diffusion-based model for synthesizing long-context, high-fidelity music efficiently.
Contributions:65 commits, 6 PRs, 24 pushes in 2 months
high-fidelitymodel-basedmidiaudiodiffusion
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.
Request Free Trial
Kinyugo Maina - Machine Learning Researcher at Self-employed