Stable Basin

2024–Present
Principal, AI Engineering Consultant
Virtual ER Platform

Built a full-stack telehealth platform from zero: patient intake portal, EHR provider UI, and a serverless backend on AWS. FHIR-based architecture on Oystehr with Auth0, appointment scheduling, lab orders, Rx, and automated billing.

  • Built an automated fax parsing pipeline that extracts patient data from incoming faxes and maps it directly to FHIR records, eliminating manual data entry.
React TypeScript AWS FHIR Healthcare
Agentic Calling System

Built a voice agent system on Retell AI that autonomously calls insurance adjusters to gather case information, replacing hours of manual outreach per claim.

  • Designed an iteration-based versioning system so the team can test and promote new agent versions without touching live calls.
  • Built an analytics suite tracking call outcomes, success rates, and campaign coverage.
Python Retell AI Temporal LLMs Insurance
Agentic Coding Framework

Designed and built an agentic coding framework that brings AI-assisted development into every phase of the SDLC, from ticket to merged code.

  • Skills map to development phases and chain: spec, build, execute, test, pre-review, MR review. Each defines explicit inputs, outputs, and checkpoints.
  • Runs inside Claude Code, Cursor, or Codex and pulls live context from Jira, Confluence, and Figma. Works across multiple repos.
Claude Code Agentic AI Developer Tooling AI Enablement

PodCore

2024
Side Project · Luz Labs
  • A podcast of a podcast. PodCore distills hour-long episodes into 5-minute audio summaries, plus a written brief with key concepts, notable quotes, and takeaways.
  • Subscribe to any show via YouTube URL and get the brief delivered to your inbox the moment a new episode drops.
Python LLMs Audio AI Google Cloud Automation

2022–Present
Luz Labs · Founder & CEO
  • Founded and launched Linda, an iOS app that conducts real-time AI interviews and transforms them into polished podcast episodes, published directly to Spotify and Apple Music.
  • Named after my mother, inspired by a road trip where I realized I'd never actually recorded her stories. Built for anyone who wants a living audio archive of their own life.
  • Users have created thousands of episodes. Average session time of 30 minutes; 45% WAU/MAU for power users.
  • Raised angel funding from Factorial Capital and Alex Chung (GIPHY founder).
Linda interview screen Linda episode screen
Voice AI iOS Consumer Funded Startup

GIPHY

2013–2024
Founding Engineer → VP of Product, ML
Engineering · 2013–2018
  • First engineer. Built much of the foundational infrastructure: the website, v2 web crawlers, and early content pipelines. Contributed to the API and search engine from the ground up.
  • Built foundational systems for a platform that scaled to 2–3 billion daily searches and hundreds of millions of users worldwide.
  • Took on the company's most forward-looking technical problems independently, laying the groundwork for GIPHY's ML org.
ML & Product · 2018–2024
  • Built and led GIPHY's ML org from the ground up. Grew to a team of 5 ML engineers covering search, recommendations, content intelligence, and generative content.
  • Trained and open-sourced GIPHY's celebrity detection model, a custom CNN identifying 2,300+ celebrities at 98% accuracy.
  • Built GIPHY2Vec, an in-house NLP model for content recommendations and semantic KNN search.
  • Integrated vector search across GIPHY's core search product, achieving 50–200% CTR lift on long-tail queries.
  • Built a semantic query clustering microservice that enabled a 5–10x increase in advertiser keyword inventory.
  • Fine-tuned generative models for production use: AnimateDiff for video content, CLIP for recommendations, LLMs for search taxonomy.
ML Infrastructure Search & Discovery Scale Generative AI

Atlanta Tech Village

2024–Present
Advisor

Part of Atlanta Tech Village's selective advisor program, working with early-stage startups on AI, fundraising, product strategy, team building, and engineering.

The Global Jukebox

2016–2017
Consulting Engineer
  • Migrated Alan Lomax's Global Jukebox, a vast ethnomusicology archive, off a local Java server and into a cloud-hosted Django API with a queryable database.
  • Uploaded thousands of field recordings and audio files to cloud storage, making them publicly accessible for the first time at scale.
  • The project launched to New York Times coverage in July 2017.
Django Cultural Preservation Cloud Migration

Rhizome at the New Museum

2008–2012
Director of Technology
  • Migrated Rhizome's sprawling PHP codebase to Django, modernizing the platform for one of the world's leading digital art organizations.
  • Rebuilt the ArtBase, Rhizome's archive of born-digital artworks, into a custom museum management CMS.
  • Collaborated with the Getty to develop a new ontology for describing and classifying digital artworks.
Django Digital Art Archival Systems

I take on a small number of engagements at a time. I work directly with founders and engineering leads, and I do the hands-on work.

Agentic Systems

Voice agents, coding agents, multi-step orchestration pipelines. I've built these across insurance, healthcare, and developer tooling.

AI Strategy and Enablement

Where AI fits in your stack, what to build vs. buy, and how to build the internal practices that make adoption stick.

Platform and Product Build

Full-stack AI-powered platforms from architecture to production. Useful when you have a clear problem and need a technical lead who can also make product decisions.

Based in Atlanta, GA. Available for remote and on-site engagements. Reach out at jnhasty@gmail.com.

2025
What Can AI Do for Me?, Panel, Atlanta Tech Village, Atlanta Tech Week
Practical AI adoption for non-technical founders and executives.
2025
Re:Imagine Creativity in the Age of AI, Panel, Tech Square ATL / GA Tech
How generative AI is reshaping creative industries.
2025
Building conversational AI for healthcare and the story behind Linda.
2025
Where voice and conversational agents are headed.
2023
What generative models reveal about the nature of creativity and intelligence.
2023
On generative AI and machine creativity.
2021
How GIPHY built its in-house NLP model for content recommendations and search.
2019
Building and open-sourcing a custom CNN that identifies 2,300+ celebrities at 98% accuracy.
2018
Google Cloud Next '18, San Francisco
Co-presented with Google Cloud on how GIPHY used ML to auto-tag content at scale.
2018
Train AI 2018, San Francisco
Applied machine learning in production systems.
arXiv (2020) · Self-attention aggregation network for video face representation and recognition, arXiv:2010.05340