Profile

John Houghton

Senior data and AI engineer in San Diego. Economist by training, builder by habit. Available for consulting engagements and select full-time roles.

Portfolio

Things I've built

SD Open Data Pipeline

End-to-end pipeline for San Diego open data: Dagster orchestration, dbt models, DuckDB spatial joins to council districts, and CI with full test coverage.

DagsterdbtDuckDB spatialCI
sd-open-data-pipeline

LLM Dataset Curation

Config-driven curation for language-model datasets: normalization, exact and MinHash near-dedupe, Gopher/C4 quality filters, PII redaction, toxicity filtering and an eval report.

LLMsdata quality
llm-dataset-curation

Vision Lab · Local AI Showcase

Real-time camera vision and voice agents running fully on-device on a Mac Studio M3 Ultra, with event recording, data-quality checks and privacy redaction.

on-devicevisionvoice
vision-lab

Finance Wizard

An agent-first personal finance app: FastAPI and React with interactive ECharts models, scenarios and dashboards.

FastAPIReactagents
finance-wizard-demo

Personal Finance Lake

A local lakehouse on DuckDB and dbt that ingests bank feeds, enriches transactions and reconciles them nightly.

DuckDBdbtlaunchd
finance-lake-demo

Multi-Agent Assistant

A team of cooperating AI agents for research, scheduling, note-keeping and security review, with human approval on every outbound action.

agentsorchestration
multi-agent-assistant

Distributed Multimedia ETL Pipeline

Distributed image ETL on LAION-400M samples: Spark hashing and metadata extraction, exact and perceptual near-dedupe, WebP compression, and Delta Lake medallion tables orchestrated by Airflow.

SparkDelta LakeAirflow
Distributed-Multimedia-ETL-Pipeline

Multi-Provider LangChain

FastAPI and LangChain backend with a lightweight web UI for switching between Anthropic and xAI models at runtime, with chat, canvas and real-time Grok voice modes.

LangChainFastAPIvoice
multi-provider-langchain
Experience

Where I've worked

Meta (contract) — Data Engineer · 2022–2026Supported FAIR (AI research) and Reality Labs with data pipelines and analytics infrastructure. Assignment concluded September 2026.
Apple — Apple MapsData engineering for maps data and quality. TODO years + one highlight
Kaiser PermanenteHealthcare data and analytics. TODO years + one highlight
IntuitAnalytics and data for financial products. TODO years + one highlight
Background

Education & training

B.A. Economics

San Diego State University, 2011

Machine Learning Specialization

University of Washington, 2017

Data Mining Certificate

UC San Diego Extension, 2017

Interests

Outside the terminal

Local-first and private AI, economics and markets, civic open data, and rare books. TODO confirm / add interests (e.g. endurance sports)

Let's talk.

Consulting inquiries and hiring conversations welcome.