Patrick Eddy

Applied AI Product Engineer

Product engineer · Search, RAG, recommendations, learning systems

I build AI features end to end and ship them to production.

I’m a software engineer with 12+ years across full-stack product engineering, platform work, and applied AI. Currently building AI systems for medical education: semantic search, RAG, recommendations, and personalized study plans for clinicians.

Washington-based · Hawaii/HST-friendly · U.S. remote

You're inside an embedding space, the kind of system I build. Scroll to travel through it.

See the 3D version of this site

Portrait of Patrick Eddy
Patrick Eddy

Work I'm drawn to

I like building product features that use AI where it actually helps: shipping the first useful version, integrating it with real systems and data, measuring whether it works, and turning repeated needs into reusable product capabilities.

This overlaps with work often called AI product engineering, applied AI engineering, or product engineering for AI systems.

Retrieval-augmented search

Semantic search across a clinical learning library

Built retrieval-augmented semantic search to help clinicians find relevant learning content by meaning, not just keywords. Work included embeddings, pgvector/Postgres, retrieval strategy, product integration, and production rollout.

  • RAG
  • OpenAI embeddings
  • pgvector
  • Postgres
  • Search UX

Recent applied-AI work for medical education, used in production by thousands of clinicians.

Personalized recommendations

Behavior-driven recommendations

Built personalized recommendations that adapt to member behavior and content relationships. Designed the recommendation logic, data model, retrieval strategy, and full-stack product integration.

  • Recommendations
  • Personalization
  • Product engineering
  • Content discovery

Assessment-driven personalization

Assessment-to-study-plan pipeline

Turned group-level assessment misses into targeted study recommendations. Connected assessment data, content mapping, retrieval, reranking, and product UX to help teams identify and close knowledge gaps.

  • Data pipelines
  • Reranking
  • RAG
  • Learning systems

In progress In progress

Personalized retention engine

Building a daily learning plan that combines spaced repetition, recommendations, and retrieval to help clinicians retain important material over time.

  • Spaced repetition
  • Retention
  • Personalization
  • Applied AI

How I work

I’m comfortable starting with unclear requirements, legacy constraints, partial data, and real users who do not care about AI for its own sake. The work I enjoy most is turning that ambiguity into useful, reliable product behavior.

  • Frame Understand user pain, constraints, and success criteria.
  • Build Prototype quickly, then turn the useful parts into production-grade systems.
  • Integrate Connect AI features to existing data models, APIs, auth, and product surfaces.
  • Measure Evaluate relevance, adoption, latency, cost, reliability, and user trust.
  • Productize Turn repeated needs into reusable product capabilities instead of one-off hacks.

Tools I reach for

AI / retrieval

OpenAI, embeddings, RAG, reranking, pgvector, vector search, LangChain, evaluation patterns

Product engineering

TypeScript, React, Node.js, Postgres, GraphQL/REST, full-stack product architecture

Production reality

APIs, data modeling, observability, auth, performance, cost/latency tradeoffs, production debugging

Also shipped

Node.js, Ruby on Rails, React Native/Expo, native Android and iOS; earlier work in Go, Python, and Java

2023 — Present

Hippo Education

Senior Software Engineer, Platform / Applied AI

Designing and shipping net-new AI product features for medical education, including semantic search, RAG, recommendations, assessment-based study plans, and personalized retention tooling for clinicians. Also re-platformed mobile from bare React Native to Expo/EAS and migrated the backend from Firebase to GraphQL/Postgres.

Featured: Production AI learning systems for clinicians ↗

2021 — 2022

Made Renovation

Engineering Manager & Senior Software Engineer

Managed a team of 5 engineers on core services — sales, fulfillment, invoicing, and project timelines. Built the CI/CD and red/green deployment process, and migrated a legacy system managing 1k+ renovations to a new integrated sales + fulfillment platform.

2018 — 2021

Varsity Tutors

Software Engineer, Sales Ops

Built checkout, payment, enrollment, and internal sales tools for a high-throughput education marketplace.

Let's talk

Building AI features into a real product?

p@patrickeddy.com

Washington-based · Hawaii/HST-friendly · U.S. remote

© 2026 Patrick Eddy