case study Applied AI · Medical education
Case Study: Production AI Learning Systems for Clinicians
A look at recent applied-AI work in medical education: semantic search, RAG, recommendations, and personalized learning workflows designed to help clinicians find and retain relevant material.
Problem
Clinicians have limited time, large content libraries, and uneven knowledge gaps. The product needed better ways to surface relevant learning material at the right moment.
Role
Owned key applied-AI product work end to end: discovery, architecture, implementation, product integration, production rollout, and iteration.
Built
- Semantic search over clinical education content
- RAG/retrieval layer for content discovery
- Personalized recommendations
- Assessment-based study plan recommendations
- pgvector/Postgres data model
- OpenAI embeddings integration
- Reranking and relevance-improvement workflows
- Full-stack product integration
Production concerns
- Retrieval relevance
- Latency
- Cost
- Content freshness
- User trust
- Fallback behavior
- Evaluation
- Maintainability
Impact
Shipped applied-AI systems into production for clinician-facing learning workflows, used in production by thousands of clinicians.
This is the kind of work I enjoy most: start with an ambiguous workflow, build the technical system, ship it into production, measure whether it helps, and turn the pattern into reusable product infrastructure.
Washington-based · Hawaii/HST-friendly · U.S. remote