~/work5 roles · 2022 — 2026
Four years of the same question.
Each of these ended up being a version of one problem: how do you know the output is right. Listed newest first — the dates carry the information.
- 01May 2026
— July 2026
01Ryniant
Founding Engineer · AI drug-synthesis platformRebuilt a synthesis-planning product so that nothing reaches a chemist unless it has been computed or found in the literature.100% of displayed values structure-computed or literature-verified+25% discoverable synthesis routeshours → minutes synthesis planning timeRead → - 02September 2025
— May 2026
02UCLA NLP Lab
Machine Learning Researcher · LLM interpretabilityLocated the components inside open-source language models responsible for hallucination, then intervened on them to prove the relationship was causal.6 / 32 layers carrying most reasoning-relevant signal3 attention heads necessary for hallucination behavior16 monosemantic features tied to hallucination-prone reasoning−30% hallucination rate under steering interventionRead → - 03June 2025
— September 2025
03Genter Capital Management
Data Analyst Intern · Wealth management firmAutomated an IRS-mandated compliance calculation across 200+ client accounts, where the cost of a wrong number is a federal penalty.200+ client accounts under automated RMD calculation~40 hrs saved during compliance season3+ hrs/wk cut from portfolio reportingRead → - 04January 2025
— June 2025
04Chelle AI
Machine Learning Engineer · LLM-based learning platformReplaced gut-feel prompt engineering with a rubric-based evaluation framework and automated scoring loops.−25% hallucination rate after rubric-driven prompt selection+18% student engagement scoresRead → - 05August 2022
— August 2023
05Sentiment Systems
Backend Engineer · Health clinic startupBuilt the NLP pipeline and multi-tenant backend that let clinics read patient sentiment without reading every entry.−30% clinical reporting timeRead →