AI for Data Teams, Healthcare Edition: 2 Day Hands-On Workshop
Eric Just
25+ Years of Healthcare Data Expertise
Data Teams + AI: Building the Next Generation of Data Pipelines
This course explores a privacy-first AI ecosystem built around local AI models, information extraction, document understanding, semantic search, retrieval, classification, and multimodal data processing.
In this hands-on course, you'll learn how these technologies work and combine them into practical data pipelines. Within the first 30 minutes, you'll run AI models locally. By the end of the course, you'll have built AI workflows that process documents, extract structured information, benchmark model performance, and power a working RAG system.
A core theme of the course is AI sovereignty. By learning to run models locally, you'll gain the freedom to choose a privacy-first path to AI, maintain control of sensitive data, and make informed decisions about when cloud-based services add value.
These same capabilities form the foundation of modern agentic AI. Before agents can act, they need reliable access to information. This course teaches the building blocks behind those systems.
While examples are drawn from healthcare, the techniques apply broadly to any team working with documents, text, and unstructured data. No healthcare background is required.
What you’ll learn
Move Beyond Prompting and Learn How Modern AI Systems Are Built
Run modern AI models on commodity hardware
Build privacy-first workflows for sensitive data
Reduce dependence on cloud-based AI services
Understand the strengths and tradeoffs of different AI model types
Learn the difference between decoders, encoders, cross-encoders, and extraction models
Evaluate AI approaches based on accuracy, speed, cost, and privacy
Transform unstructured documents into structured data
Extract valuable information from clinical text
Combine text, documents, and structured data into intelligent workflows
Create a Retrieval-Augmented Generation database from real documents
Understand retrieval, reranking, and context engineering
Learn where RAG works—and where it doesn't
Explore real-world challenges working with clinical and genomic data
Extract structured information from complex clinical documents
Build a multimodal pipeline combining clinical and laboratory data
Learn directly from Eric
Eric Just
25+ Data Practitioner: Developer, Architect, Executive, Founder. AI Builder.
Who this course is for
Data Engineers, Analysts, and Architects: You build data pipelines or analyze data and want to understand how AI can enhance data workflows.
Managers, Directors, and Data Leaders: You want to understand how AI is changing the capabilities, tools, and skills of modern data teams.
Product Managers: You manage and make decisions about data-focused products or applications.
What's included
Live sessions
Learn directly from Eric Just in a real-time, interactive format.
Lecture + Lab-based instruction
Slide materials are presented in an approachable way. When we discuss an approach, we present alternative approaches because there is more than one way with this rapidly evolving toolkit. Labs are engaging and help students see how things work. Students can run/manipulate/build on code. Lab work is python-based in Jupyter notebooks.
Hands-on Lab Environment: Yours to Keep After Course
All you need is browser access. You will get an email with a link to your lab environment, containing code you will run. At the conclusion, you will be able to download your containerized lab environment and run it locally... forever.
Lifetime access
Go back to course content and recordings whenever you need to.
Community of peers
Stay accountable and share insights with like-minded professionals.
Certificate of completion
Share your new skills with your employer or on LinkedIn.
Maven Guarantee
Your purchase is backed by the Maven Guarantee.
Course syllabus
Week 1
Jul
14
Day 1: Foundations of AI-Powered Data Pipelines
Jul
15
Day 2: Retrieval, Benchmarking, And Multimodal Data Pipelines
Schedule
Live sessions
12 hrs
All course content and hands-on work is part of the live sessions. We will work through examples together.
Tue, Jul 14
3:00 PM—9:00 PM (UTC)
Wed, Jul 15
3:00 PM—9:00 PM (UTC)
Frequently asked questions
Feedback from Students
"The sessions gave me a much clearer understanding of key concepts -- local LLM setup, building user interfaces, making API calls, and working with embeddings and vector databases, etc. It opened a new door for me in thinking about how AI can support oncology research."
-- Senior Design Engineer, Huntsman Cancer Institute
"The feedback has been entirely positive. One comment I keep getting is that people didn’t realize that there are useful applications of LLMs that do not require powerful GPUs."
-- Director, Comprehensive Oncology Data & Engineering (CODE), Huntsman Cancer Institute
"It was impressive that you built something that started very accessible and built up into real world examples. I feel more confident in engaging in our AI convos at Manifold."
-- Product Manager, Manifold.ai
Maven for Teams
Reimbursement
Get your company to pay
Everything L&D needs: email template, receipts, and certificate of completion.
Get reimbursedTeam discount
Learn with your teammates
Save 20%+ when 2 or more teammates enroll in the same cohort.
Save 20%+ with a teamPrivate cohort
Run a cohort for your org
A dedicated cohort with a custom schedule and curriculum, tailored to your team.
Book a private cohort$1,200
USD