Richhiey Thomas

Hey there! Richhiey here.

I build end-to-end machine learning systems, with a focus on audio ML (music transcription, event detection, and ASR). I work across data pipelines, real-time modeling, and cloud deployment using Python, TypeScript, and C++.

My stack includes AWS (SageMaker, Glue, S3, ECS), Docker, FastAPI/Flask, PySpark, and Airflow for scalable and production-ready ML workflows.

If you’re into audio AI, data engineering, or practical ML systems, let’s connect.