Machine Learning Specialist
Patrick Deziel
Distributed Systems Engineer
Bio
Patrick Deziel is a distributed systems engineer and machine learning specialist. Patrick has extensive experience building and maintaining mission-critical systems in the private sector, as well as integrating modern ML solutions into existing applications. At Rotational, he designs and builds intelligent distributed systems to enable global use cases. In his free time, Patrick enjoys rock climbing and consuming science fiction.
Blog Posts Written by Patrick
Teaching LLMs With Continuous Human Feedback
If you’ve worked with generative AI models you know they can be fickle and sometimes fail to meet the expectations of users. How can we move towards models users trust and see clear value in? Let’s engineer a user-feedback loop!
Sep 13, 2024Building an AI Text Detector - Lessons Learned
The LLMs boom has made differentiating text written by a person vs. generated by AI a highly desired technology. In this post, I’ll attempt to build an AI text detector from scratch!
May 15, 2024Predicting the Oscars With LLMs
Looking for a middle ground between custom LLMs and traditional ML? Please welcome semantic search to the stage! Let’s use semantic search to predict which film will take home the “Best Picture” Oscar this year 🤩
Mar 8, 2024Build Your Own LLM - Getting Into Production
If you’re building LLMs but have no way to deploy them, are they even useful? In this post, you’ll deploy an LLM into a live production application!
Feb 9, 2024Build Your Own LLM - Training
If you want to protect your IP or avoid vendor lock, you may find that building your own LLM is more practical than relying on services like ChatGPT. In this post, you’ll train a custom LLM using your own data!
Feb 6, 2024Build Your Own LLM - Data Ingestion
2023 was the year of large language models (LLMs) due to services like ChatGPT and Stable Diffusion gaining mainstream attention. In this series, learn about the architecture behind LLMs and how to build your own custom LLM!
Jan 15, 2024