Applied AI Product Engineer
I build AI features end to end and ship them to production.
12+ years of full-stack product engineering. Currently shipping semantic search, RAG, recommendations, and study plans for clinicians.
Washington-based · Hawaii/HST-friendly · U.S. remote
You're inside an embedding space. Scroll to travel through it.
Work I'm drawn to
AI where it actually helps: ship the first useful version, wire it into real data, measure it, then make it reusable.
Also called AI product engineering or applied AI engineering.
Retrieval-augmented search
Semantic search across a clinical learning library
Search by meaning, not keywords. Embeddings, pgvector, retrieval strategy, and the rollout.
- RAG
- OpenAI embeddings
- pgvector
- Postgres
- Search UX
In production for thousands of clinicians.
Personalized recommendations
Behavior-driven recommendations
Recommendations that follow what members do. Logic, data model, retrieval, and the full-stack integration.
- Recommendations
- Personalization
- Product engineering
- Content discovery
Assessment-driven personalization
Assessment-to-study-plan pipeline
Assessment misses become targeted study plans. Content mapping, retrieval, reranking, and the UX.
- Data pipelines
- Reranking
- RAG
- Learning systems
In progress In progress
Personalized retention engine
A daily plan that mixes spaced repetition, recommendations, and retrieval so material sticks.
- Spaced repetition
- Retention
- Personalization
- Applied AI
How I work
Unclear requirements, legacy constraints, partial data, users who do not care about AI. I turn that ambiguity into reliable product behavior.
- Frame User pain, constraints, success criteria.
- Build Prototype fast, then harden what works.
- Integrate Existing data models, APIs, auth, surfaces.
- Measure Relevance, adoption, latency, cost, trust.
- Productize Repeated needs become reusable capabilities.
Tools I reach for
AI / retrieval
OpenAI, embeddings, RAG, reranking, pgvector, evals
Product engineering
TypeScript, React, Node.js, Postgres, GraphQL/REST
Production reality
Observability, auth, performance, cost/latency, debugging
Also shipped
Rails, React Native/Expo, native iOS/Android, Go, Python
2023 — Present
Hippo Education
Senior Software Engineer, Platform / Applied AI
Net-new AI features for clinicians: semantic search, RAG, recommendations, study plans. Also moved mobile to Expo/EAS and the backend from Firebase to GraphQL/Postgres.
2021 — 2022
Made Renovation
Engineering Manager & Senior Software Engineer
Managed 5 engineers on sales, fulfillment, and invoicing. Built CI/CD and migrated 1k+ renovations to a new platform.
2018 — 2021
Varsity Tutors
Software Engineer, Sales Ops
Checkout, payments, enrollment, and sales tools for an education marketplace.
Let's talk
Building AI features into a real product?
p@patrickeddy.comWashington-based · Hawaii/HST-friendly · U.S. remote
© 2026 Patrick Eddy