I am a Software Engineer and AI Researcher with over 7 years of experience building scalable systems across telecommunications, cloud platforms, and generative AI.
My research focuses on Natural Language Processing for low-resource languages, particularly Swahili, and improving prosody in AI speech systems.
I bridge research and real-world deployment by building production-grade systems powered by modern AI models.
SwaRegex: A lexical transducer for the morphological segmentation of Swahili verbs
Muthee, M.G., Makau, M., Amos, O. (2022)
African Journal of Science, Technology and Social Sciences
Ongoing Research:
Developing a hybrid morphological analysis framework that integrates rule-based lexical transducers (SwaRegex)
with supervised deep learning models (e.g., character-level BiLSTM-CRF) for accurate segmentation of
Swahili verbs. This work aims to improve linguistic representation and downstream performance in
NLP systems for low-resource languages.
Email: rescostech@gmail.com