Hannes Hapke is a machine learning engineer with a focus on machine learning engineering and natural language applications. He loves solving practical ML problems, from framing the question to building systems that hold up in production, and has deployed transformer-based models at scale, including work on optimizing inference latency for CPU instances at digits.com.

Hannes is a co-author of Building Machine Learning Pipelines, published by O’Reilly, a book that guides teams through productionizing machine learning, from data ingestion and modeling to deployment and monitoring. He shares his work and experiments through open source and his personal site.