Building LLM Applications for Data Scientists and Software Engineers

New
·

4 Weeks

·

Cohort-based Course

Build LLM-powered software reliably & from first principles. Learn the GenAI software development lifecycle: agents, evals, iteration & more

This course is popular

5 people enrolled last week.

Experience building and lecturing at

Stitch Fix
LinkedIn
Outerbounds
Stanford University
Yale University

Course overview

Ground principles that underpin successful GenAI app development

Enroll in this course now for early bird pricing of $800. On December 1st, the cost will revert to the regular cost of $1,000.


It's easy to build a generative AI POC but turning it into robust, reliable software that scales is difficult: most of us still end up in "POC purgatory".


It doesn't have to be this way.


Using the right principles and human-centric tools, you can take proof of concept LLM-powered demos and turn them into robust software.


In this course, you'll learn the first principles necessary to ship robust and reliable LLM applications, along with developing the technical chops and iterative product development mindset necessary.


Course content

- How to integrate AI models and APIs into a practical application.

- Techniques to manage non-determinism and optimize outputs through prompt engineering.

- How to monitor, log, and evaluate AI systems to ensure reliability.

- The importance of handling structured - outputs and using function calling in AI models.

- The software engineering side of building AI systems, including iterative development, debugging, and performance monitoring.

- Practical experience in building an app to query PDFs using multimodal models.


The course includes

- Hands-on sessions building and using LLM applications

- Iteration and experimentation to improve GenAI applications

- Group discussions and reflection on the building process and the end-user experience

- Q&As with expert practitioners


API Credits


- Modal (serverless cloud infrastructure for AI, ML, and data applications) is generously providing $1,000 worth of credits for all students!

- Watch this space for announcement of more API credits you will receive in this course.

Who is this course for

01

Data scientists, machine learning engineers who are sick & tired of seeing and building prototypes & want to ship reliable LLM applications

02

Software engineers who want to learn how to build Generative AI systems and learn the LLM software development lifecycle.

What you’ll get out of this course

How to integrate AI models and APIs into a practical application.

Over the course we'll build out a simple AI application to ground the principles in the course. We'll successively add to it, and take if from a simple LLM pipeline that processes a PDF, to something that also has some agentic behavior.

Techniques to manage non-determinism and optimize outputs through prompt engineering.

We will show case practical approaches to improving and evaluating your prompts and application outcomes.

How to monitor, log, and evaluate AI systems to ensure reliability.

We'll demystify the engineering required behind these solutions so you can choose to implement them yourself.

The software engineering side of building AI systems, including iterative development, debugging, and performance monitoring.

You'll leave with a better understanding of what is going on, and how to construct a software development lifecycle that fits your reliability needs.

This course includes

8 interactive live sessions

Lifetime access to course materials

11 in-depth lessons

Direct access to instructor

Projects to apply learnings

Guided feedback & reflection

Private community of peers

Course certificate upon completion

Maven Satisfaction Guarantee

This course is backed by Maven’s guarantee. You can receive a full refund within 14 days after the course ends, provided you meet the completion criteria in our refund policy.

Course syllabus

Week 1

Jan 6—Jan 12

    Building Your First LLM-Powered Application

    5 items

    Jan

    7

    Live Session 1

    Tue 1/712:00 AM—2:00 AM (UTC)

    Jan

    9

    Live Session 2

    Thu 1/912:00 AM—2:00 AM (UTC)

Week 2

Jan 13—Jan 19

    The Importance of Monitoring and Evaluating Your GenAI Software

    3 items

    Jan

    14

    Session 3

    Tue 1/1412:00 AM—2:00 AM (UTC)

    Jan

    16

    Session 4

    Thu 1/1612:00 AM—2:00 AM (UTC)

Week 3

Jan 20—Jan 26

    The Flywheel of Iterative Improvement to your MVP

    1 item

    Jan

    21

    Session 5

    Tue 1/2112:00 AM—2:00 AM (UTC)

    Jan

    23

    Session 6

    Thu 1/2312:00 AM—2:00 AM (UTC)

Week 4

Jan 27—Jan 31

    Promoting Your LLM Application to Production

    2 items

    Jan

    28

    Session 7

    Tue 1/2812:00 AM—2:00 AM (UTC)

    Jan

    30

    Session 8

    Thu 1/3012:00 AM—2:00 AM (UTC)

What people are saying

        Stefan & Hugo are two of the best educators in this space. You'll learn a lot from their practical and pragmatic insights to building reliable AI.
Elijah ben Izzy

Elijah ben Izzy

Co-founder & CTO DAGWorks Inc.
        I want to take this course.
Hamel Husain

Hamel Husain

AI Engineer, Parlance Labs

Meet your instructor

Hugo Bowne-Anderson

Hugo Bowne-Anderson

Host of Vanishing Gradients podcast; ex-Outerbounds; expert in DS/ML.

Hugo Bowne-Anderson is an independent data and AI consultant with extensive experience in the tech industry. He is the host of the industry Vanishing Gradients, where he explores cutting-edge developments in data science and artificial intelligence. As a data scientist, educator, evangelist, content marketer, and strategist, Hugo has worked with leading companies in the field. His past roles include Head of Developer Relations at Outerbounds, a company committed to building infrastructure for machine learning applications, and positions at Coiled and DataCamp, where he focused on scaling data science and online education respectively. Hugo's teaching experience spans from institutions like Yale University and Cold Spring Harbor Laboratory to conferences such as SciPy, PyCon, and ODSC. He has also worked with organizations like Data Carpentry to promote data literacy. His impact on data science education is significant, having developed over 30 courses on the DataCamp platform that have reached more than 3 million learners worldwide. Hugo also created and hosted the popular weekly data industry podcast DataFramed for two years. Committed to democratizing data skills and access to data science tools, Hugo advocates for open source software both for individuals and enterprises.

Stefan Krawczyk

Stefan Krawczyk

Ex-Stitch Fix; 13+ Years building / productionizing data, ML, and AI

Stefan Krawczyk is the co-founder and CEO of DAGWorks, an open-source company driving two projects: Hamilton & Burr, whose mission to empower developers to build reliable AI agents & applications. He is a Y Combinator alum, StartX alum, and a Stanford graduate with a Master of Science in Computer Science with Distinction in Research. He has over thirteen years of experience in building and leading data & ML-related systems and teams, at companies like Stitch Fix, Idibon, Nextdoor, and Linkedin, his passion is to make others more successful with data by bridging the engineering gap between data science, machine learning, artificial intelligence, and the business. 

A pattern of wavy dots

Join an upcoming cohort

Building LLM Applications for Data Scientists and Software Engineers

Cohort 1

$800

Dates

Jan 6—31, 2025

Payment Deadline

Jan 7, 2025
Get reimbursed

Course schedule

4-6 hours per week

  • Mondays and Wednesdays

    4:00pm - 6:00pm PST

    Live in person sessions. We'll finalize session times by mid-November.

  • Weekly projects

    2 hours per week

    To ensure hands-on practical time, there will be project work to complete throughout the course.

Learning is better with cohorts

Learning is better with cohorts

Active hands-on learning

This course builds on live workshops and hands-on projects

Interactive and project-based

You’ll be interacting with other learners through breakout rooms and project teams

Learn with a cohort of peers

Join a community of like-minded people who want to learn and grow alongside you

Frequently Asked Questions

A pattern of wavy dots

Join an upcoming cohort

Building LLM Applications for Data Scientists and Software Engineers

Cohort 1

$800

Dates

Jan 6—31, 2025

Payment Deadline

Jan 7, 2025
Get reimbursed

$800

4 Weeks