Senior Applied AI Scientist & Data Scientist · Seattle, WA

I deploy Agentsforward, into livepartner operations.

I build ML systems in healthcare that ship to production and move real numbers, from a $10M claims-audit randomized controlled trial to agentic ChatGPT evaluated in the real world.

Experience Get in touch

01What I do

I'm a Senior Applied AI Scientist & Data Scientist working at the seam between healthcare research and production. I take models the whole way, ETL, evaluation, and monitoring included, so they still move real numbers months after launch. Most recently I forward-deployed at R1 RCM, delivering $13M in error reduction on a real-time eligibility rollout for a $31B health system that had debated the move for 18 months. At L.A. Care, the largest publicly operated health plan in the U.S., I built a claims-audit application that returned $10M in error reduction, validated by a randomized controlled trial, and shipped ChatGPT API services with CoVe hallucination control that improves medication identification for members and prevents $2M in adverse outcomes. I've also published two peer-reviewed transformer papers.

Data Science Director
R1 RCM
Apr 2026 – Jul 2026
Senior Applied AI Scientist
L.A. Care Health Plan
Feb 2023 – Apr 2026
Machine Learning Researcher
Georgia Southern University
Sep 2021 – Dec 2022

Operations, validated by RCT

At L.A. Care I built a claims-audit application for claim adjudication operations as the sole contributor, from PySpark pipelines to an ACID datastore, driving operational improvement through root-cause issue identification and resolution and returning $10M in error reduction, validated by a randomized controlled trial with real endpoints, not a notebook that scored well offline.

LLMs people can trust

Production ChatGPT API services on Azure with agentic Chain-of-Thought and CoVe hallucination control that improves medication identification for members and prevents $2M in adverse outcomes, grounded, auditable, and wired into systems people already use.

Statewide health equity

Core designer of the DHCS RSST geospatial health-improvement scoring module, built with state entities to surface equity gaps across California and deployed to a 55+ person analytics team.

02Selected work

All projects

oncolens

012026

OncoLens

A RAG system over the oncology research literature: search by concept and get back the exact paper and the passage where it appears.

A retrieval system over 3,166 peer-reviewed oncology papers (180,850 passages) from PubMed and PMC, each held as verbatim full text. Search by concept and it returns the paper and the exact passage where the concept appears, with character offsets into the source, built for the R&D question of what is known about a target, which a set of papers answers, not one. Papers are embedded with OpenAI and clustered into an interactive WebGL galaxy of the corpus, its regions auto-named from NLM's MeSH indexing.

OpenAI RAGClusteringWebGLEmbeddingsNext.js

Live GitHub

velvetoverride

022026Actively maintained

Velvet Override

An agentic AI bot that finds jobs, tailors every answer, and auto-applies, then tracks each application.

A multi-agent auto-application system: it navigates job sites, reads each posting, writes tailored cover letters and open-ended answers under hallucination control, scores experience fit, and submits, all logged to a live application tracker. (Company names in the screenshot are redacted.)

Agentic AILLMsBrowser AutomationPythonNext.js

GitHub

lahealth.tech

032025Actively maintained

LAhealth.tech

Web-mines and aggregates in-network care across Medi-Cal plans so anyone can find help they can actually reach.

Access Medi-Cal LA knocks down the barriers that keep people from care they are entitled to. It web-mines and aggregates provider and resource data across multiple Medi-Cal plans, reconciles it against L.A. Care's live FHIR directory, and surfaces in-network options a member can actually get to, ranked by distance or real travel time (walk, bike, drive) via Google Maps Platform APIs (Geocoding, Distance Matrix, Directions / Routes) on a Leaflet / OpenStreetMap map. Built for people without a car or an obvious place to start.

FHIRGoogle Maps APIsGeospatialLeafletNext.js

Live GitHub

putstrike

042025

PutStrike

An AI-powered put-option screener that ranks cash-secured put opportunities.

Screens 80+ liquid stocks with an 8-factor scoring model and forecasts prices with a hybrid of statistical ensembles and an iTransformer deep-learning model, fusing live market data, macro indicators, and 154 engineered features, with built-in backtesting.

iTransformerPyTorchNext.jsQuantPostgres

Live GitHub

Download résumé