Samuel Oyerinde is a dedicated Applied ML Engineer and NLP Researcher based in Lagos, Nigeria, specializing in building inclusive and reliable AI systems for underrepresented African languages. He earned his Bachelor of Science in Computer Science from the Federal University of Agriculture, Abeokuta (FUNAAB), where his research focused on evaluating classical machine learning models and AfriBERT for Yorùbá document classification. A recognized contributor to the African NLP ecosystem, Samuel has contributed to several high-impact peer-reviewed publications, including the MasakhaNER project, the AfriWOZ dialogue generation corpus, and The African Stopwords Project
His technical expertise is centered on speech technologies specifically Text-to-Speech (TTS) and Automatic Speech Recognition (ASR) as well as diacritic-sensitive OCR systems. Currently, he serves as an NLP and Audio Data Processing contractor for Digital Divide Data (DDD) through Masakhane Research Foundation. In this role, he manages complex end-to-end data workflows and oversees the curation of over 4,000 hours of high-quality multilingual speech data across languages such as Luhya, Kamba, Gusii, and Somali.

Beyond his research, Samuel is the architect behind edurepoai.xyz, an AI-powered admission intelligence platform designed to centralize fragmented educational data for Nigerian students. He also developed Yorùbá OCR, a specialized full-stack pipeline optimized for handling tonal diacritics. As an active community contributor, Samuel focuses on addressing data scarcity and linguistic fidelity, ensuring tonal scripts like Yorùbá are accurately represented in modern AI frameworks.