Elixir Wizards Nx and Machine Learning in Elixir with Sean Moriarity
Jun 19, 2025
Sean Moriarity, co-creator of the Nx project and author of Machine Learning in Elixir, shares his journey from military to tech, focusing on large language models. He discusses the evolving Elixir ML landscape, the strategic choice between off-the-shelf models and custom solutions, and how to effectively integrate Python libraries. Sean highlights Elixir's strengths in distributed computing for ML tasks and offers practical advice on starting ML projects, emphasizing the use of motivating use cases and domain-specific languages to enhance AI workflows.
AI Snips
Chapters
Books
Transcript
Episode notes
Military to AI Engineering
- Sean Moriarity transitioned from military service to working on large language models in the civilian tech world.
- He started at Magic in May, focusing on AI for software engineering.
Elixir as ML Orchestration Layer
- Elixir excels as an orchestration layer integrating external ML tools rather than doing it all internally.
- Combining Elixir’s orchestration with Python’s mature ML ecosystem strikes a practical balance.
Use Frontier Models First
- Use frontier models for text tasks to save on engineering and prototyping costs.
- Deploy off-the-shelf LLMs initially, then train custom models as needed.
