Building Apps with Large Language Models

This course is closed for enrollment.

"Robert's course on building applications with LLMs was great. His unique talent for simplifying complex topics made it easy for me to understand and, more importantly, apply them in real-life scenarios. Throughout the course, I encountered several nuances and challenges associated with LLMs that I wouldn't have been aware of otherwise. One aspect of the course that I particularly appreciated was its focus on practicality. Robert didn't just teach theory; he guided us through the process of shaping technical projects into prototypes that solve real-market challenges. I also really liked the sense of community within the course and collaboration with fellow students. Highly recommended!"

- Michael Hart, VP Strategy, Prescient Co.

Course Curriculum

Frequently Asked Questions

When does the course start and finish?
The course starts the Monday after the cohort opens and ends four weeks later. You have access to the material after the cohort ends.
Are refunds available if I am not happy with the course?
Yes! You may request a full refund within the first week of the cohort.
Is there an academic rate?
Yes. Proof of academic enrollment is required. Contact us for more information.
How long do I have access to the material?
You have indefinite access to the material after the conclusion of the course.
What is the basic mathematical background I need to succeed?
One should have a decent intuition for the basic math of neural networks, which is basic arithmetic observations in large dimensions. We will provide code examples in Python using mostly the Huggingface library. However, most of the work is high-level and conceptual, developed to help people quickly understand the realities of building applications with LLMs.
What programming languages and libraries do we use in the workshop?
In this workshop, we rely primarily on Python. Specifically, we rely heavily on the Huggingface Transformers library.
I do not have software engineering-level Python skills. Is this course right for me?
Yes. You just need to be comfortable with a language like Python to do a data science-style analysis. The biggest coding challenge is usually debugging code when working on homework. For that, you can get help from instructor.
What would you say would be a reasonable estimate for the amount of time required to get a good grasp of the materials?
We designed this workshop such that you may remain at a high-level view if you prefer, and you may go more in-depth and get a deep grasp of the material if you prefer. For the high-level approach, you just watch videos, and read lecture notes, read through the forum, and ask questions in calls with the instructors. That requires about an hour a day for the 4-week cohort.

Your Instructor

Robert Osazuwa Ness
Robert Osazuwa Ness

Robert is currently a research scientist at Microsoft Research and faculty at the Northeastern University department of computer science. He has worked in industry as a research engineer and data scientist building production quality systems for Bayesian decision-making under uncertainty.

Robert didn't start in machine learning. He started his career by becoming fluent in Mandarin Chinese and moving to Tibet to do developmental economics fieldwork. He later obtained a graduate degree from Johns Hopkins School of Advanced International Studies.

Robert attained his Ph. D. in mathematical statistics from Purdue University. He has published in top tier journals and venues on topics including causal inference, probabilistic modeling, sequential decision processes, and dynamic models of complex systems.