Jay Ozer · AI Engineering · San Francisco

Making complex
work feel calm.

I build production AI for industries where getting it right actually matters: document intelligence, autonomous agents, and whatever a hard problem turns out to need. Mostly I'm interested in turning messy, manual work into something dependable, and in the people I get to build it with.

See what I'm building
  • Document intelligence
  • Autonomous agents
  • Reliable by design
Jay Ozer standing beside his shadow

Selected work

Systems shipped where reliability is the product.

Production · Title insurance

IntentIQ

A two-stage AI pipeline that triages and routes 14K+ emails a day into seven title-insurance workflow categories, born from an order-volume surge that overwhelmed the ops team.

14K+ emails / dayMulti-agent · Agents SDK
Healthcare AI

PoppyNote

HIPAA-ready SOAP-note transcription for dental practices, with a Curve integration that pulls the day's patients and writes notes back automatically. Built so my wife stops staying late.

1,362 visits managedCase study
Healthcare AI

Ask Poppy

Fine-tuned GPT-4o-mini chatbot on 750+ verified Q&A pairs, the first line of defense for worried parents on on-call weekends.

24/7 liveTry it
Privacy tool

POPMedia

Browser-based media optimizer. FFmpeg.wasm compresses video entirely client-side. Your files never leave the tab.

50-90% smallerDemo
Open source · PWA

Baby Kick Count

A calm, offline-first PWA for tracking fetal movement, with no accounts, no ads, no tracking. The design DNA behind this very site.

100% privateVisit
Family app · iOS

Chloe

A local-first nursery ledger iPhone app for feeding, sleep, diapers and private voice logging, with optional Supabase sync and a small Next.js marketing/API host.

Local-first iOSRepo

Experience

A decade building systems where the rules are strict.

Doma Technology
San Francisco, CA · 2020 - Present
Senior Manager, Applied AIMar 2023 - Present

Led the applied-AI pod delivering production agentic systems for title-insurance automation, partnering with Fannie Mae and Blend.

  • Architected DeedIQ and ClerkIQ, both patent-pending, cutting processing time and per-document cost by about 99%.
  • Built CI/CD for LLM deployment with canary releases, rollback, and RAGAS quality monitoring.
  • Helped break a 30-year industry monopoly, catalyzing Doma's shift to a pure-tech platform.
Manager, Data EngineeringJul 2021 - Mar 2023

Built and led a team of six, establishing engineering rituals and modern data practices that scaled company-wide.

  • Hired and mentored 6 engineers with structured assessments and career frameworks.
  • Unified three merged companies' data into a centralized Snowflake platform.
  • 10x dashboard performance; 90% reduction in query times.
Staff Data AnalystJan 2020 - Jul 2021

Established a unified source of truth and drove company-wide adoption of modern analytics ahead of IPO.

Federal Reserve Bank of San Francisco
San Francisco, CA · 2013 - 2020
Senior Data AnalystAug 2013 - Jan 2020

Led data engineering and BI infrastructure processing terabytes of economic data for monetary-policy decisions in a highly regulated central-banking environment.

  • Architected FedQuery Hub, HDFS plus Tableau, enabling self-service analytics for policy research.
  • Built a Fed-wide data-governance framework that raised reliability across departments.

Patents

A few ideas worth filing for.

Each one started as a stubborn, manual workflow and turned into something that mostly runs itself. The filings are nice; the part I like is that they quietly save people a lot of time.

Patent pendingNo. 19/080655

DeedIQIntelligent deed analysis

LLM agents plus neural search with dual-team extraction, cross-validation, and human-in-the-loop review, replacing a brittle, manual deed workflow with a system that learns continuously.

97%+
accuracy in production
$12 to $0.20
cost per deed
LLM AgentsNeural SearchCross-ValidationHuman-in-the-Loop
Patent pendingNo. 19/436529

ClerkIQCounty document retrieval

Hybrid automation across fragmented county portals, with domain-specific parsing, template-driven scripted browsing, AI fallback, and vision verification that every document matches before delivery.

$40 to $0.50
cost per document
24/7
automated retrieval
Hybrid AutomationScripted BrowsingVision VerificationFastAPI
In preparationNo. pending

DiscoverIQAutonomous retrieval agents

An automated document retrieval system driven by autonomous agents that plan, navigate, and verify on their own, extending the IQ family beyond county records to any source of record. Details coming soon

Agentic
multi-agent orchestration
Autonomous
plan · navigate · verify
Autonomous AgentsDocument RetrievalPlaceholder

Working with people

I'd rather build the team than run it.

A decade in, the part I care about most isn't the systems. It's the people I build them with. I've hired engineers from zero, sat through the boring reviews, and learned that patience ships more than cleverness. No heroics, just steady, honest work.

0 to 6
engineers hired and grown
14+
production AI systems shipped
1000+
data-quality issues resolved via review
10+
years in regulated AI/ML

Open source & local tools

Small tools, shipped when they helped.

CanopyIQ

Local agent harness

Python-first coding-agent Kanban that turns a large goal into scoped stories, runs one worker at a time, and keeps an auditable review trail.

PythonSQLiteAgents
View repo

ForageIQ

Chrome workflow recorder

Local-export-first recorder for county sites, preserving full-tab video, DOM evidence, downloads metadata and handoff packs for county-lens.

Chrome MV3Python CLIAzure
View repo

Present

Local presentation studio

Voice Presenter turns source evidence from repos, demos, transcripts and notes into a grounded spoken product presentation with live Q&A.

Next.jsFastAPITTS
View repo

browser-use

Merged PR

Fixed a critical duplicate-download bug, hardening download handling across CDP, JS-fetch and polling paths.

PythonCDPBug Fix

Jay Marketplace

Plugin marketplace

A marketplace of installable AI-agent skill kits, including workflow orchestration, YouTube automation and video understanding tools.

PluginsSkillsClaude Code
View repo

Agentbuilder Outlook MCP

MCP Server

Production read and write MCP server for OpenAI's AgentBuilder, with dual Graph plus org-account auth. Powers IntentIQ.

FastMCPOutlookOAuth

Talmanac

iOS storytelling

Native iOS app where a parent can record a voice, generate a cozy story, and play it back later with cached audio and a local story library.

SwiftUIVercelElevenLabs
View repo

KnowledgeFlow

Streamlit tool

Edit-before-upload document prep for Voiceflow RAG. The community adopted it; Voiceflow shipped the idea natively.

RAGStreamlitContextual Retrieval

GuardGroq

Library

Ultra-fast LLaMA Guard guardrails for Voiceflow via Groq, real-time content safety with minimal latency.

LLaMA GuardGroqSafety

MCP jozer

MCP Server

14 standardized tools exposing my own bio, experience and CV over the Model Context Protocol. Built in under an hour.

FastMCPPersonal APIPython

Ralph

PRD agent loop

A transparent, PRD-driven Bash loop for fresh-context coding iterations across Claude Code, OpenAI Codex and Kimi CLI.

BashPRDCodex
View repo

Roast My Snack

Hackathon · 2nd place

Turns a snack photo into a 4-panel comic where a Gen-Z tooth mascot roasts its threat to your smile. Gemini plus Nano-Banana.

GeminiFastAPIQdrant

Ask Jay

Chat with my work, not just read about it.

A retrieval-augmented agent grounded in my notes, projects and patents. Ask how a system is put together, how I think about a hard problem, or just say hi. It answers with citations.

Education & credentials

Four degrees, four disciplines.

MS, Data ScienceRegis University
Denver, CO
MBA, Sustainable BusinessSan Francisco State University
San Francisco, CA
MS, Industrial EngineeringUniversity of Central Florida
Orlando, FL
BEng, Chemical EngineeringNewcastle University
UK

Certifications

AI Engineering Bootcamp
AI Makerspace · Teaching Assistant, Cohort 6, mentoring engineers in production LLM, RAG and multi-agent systems.
Advanced LLM Application Building and Fine-Tuning
Maven
Voiceflow Expert Contributor
Featured developer-meetup speaker, KnowledgeFlow and GuardGroq
Jay Ozer smiling in a dark jacket

About

From competitive sport to production AI.

I grew up in Istanbul, played competitive sports, and came up through engineering before finding my way into data and AI. Sport taught me what I still lead by: you rarely win by being exceptional at one thing. You win by being above average at many, and combining them well.

Home is San Francisco, with my wife Andrea, our daughter Chloe, and our dog Hawley. When I'm not shipping, you'll find me at the gym or out on a long walk.

SF
based in San Francisco
3
my whole world: Andrea, Chloe and Hawley
10+
years building data and AI
Chloe smiling at home
Hawley the dog resting outside
Andrea holding Chloe and smiling at home

Say hello

Let's work on something good together.

I love comparing notes with people building thoughtful AI, a hard problem, a half-formed idea, or just a good conversation. If you're making something interesting, I'd genuinely like to hear about it.

or quietly take a look at my resume