Tobi Olatunji is a Founder and clinical ML researcher with nine years of experience bridging medicine and machine learning to build scalable health technologies that improve care delivery. A former practicing MD who left clinical practice to engineer context-driven solutions, he has led clinical NLP and speech projects at AWS, Enlitic and now Intron Voice AI, where he’s developing speech recognition across 200+ accents to dramatically cut clinician documentation time. He combines deep clinical domain knowledge, MS-level CS training, and hands-on TypeScript/Python development to deliver production-ready models for NER, relation extraction, information retrieval and clinical annotation QC. An active open-source contributor, he improved Gensim’s LDA tests and implemented an EnsembleLda feature, reflecting a pragmatic focus on reproducibility and tooling. He advises global health initiatives (Harvard, OpenNotes, Commonwealth) and runs Bio-RAMP Labs to amplify minority researchers, demonstrating a rare mix of product leadership, policy influence, and commitment to equitable AI in healthcare.
9 years of coding experience
9 years of employment as a software developer
Master’s Degree Medical Informatics, Master’s Degree Medical Informatics at University of San Francisco
Certificate Healthcare Management, Certificate Healthcare Management at Yale School of Management
Certificate NYU Tandon Bridge to CS, Certificate NYU Tandon Bridge to CS at New York University
Doctor of Medicine (M.D.) Medicine and Surgery, Doctor of Medicine (M.D.) Medicine and Surgery at University of Ibadan
Master of Science - MS Computer Science, Master of Science - MS Computer Science at Georgia Institute of Technology
Contributions:13 reviews, 6 commits, 11 PRs in 1 year 8 months
Contributions summary:Tobi made several contributions focused on improving the Gensim library, particularly in the areas of topic modeling and word embeddings. They fixed a broken link in the documentation and clarified the use of random states within the LDA model. Furthermore, they transformed test names to snake_case for better code style and added tests for the `sync_state` method in the LDA model. The user also implemented the EnsembleLda feature, which included several improvements and optimizations.
Contributions:22 commits, 21 pushes, 1 branch in 2 months
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.