Selected work
I'm too cynical to say that I'm proud of anything, but here are some things that I have spent significant time on: the product I've been building, and the open-source research code from my years at Microsoft. Every entry links to the real thing.
building now
founder & technical lead · live in the app stores
Task management for ground-level teams: dispatchers, coordinators, and operators. Create a task by voice or text, assign it to anyone (even people who don't have the app), and track status as updates come back by SMS or email. I own the whole system, from the mobile client to the backend.
React Native (iOS + Android) · Django on DigitalOcean · in-app AI · two-way Google sync · CI/CD, analytics, error monitoring
open source · research
Code and datasets behind papers I co-authored at Microsoft, released so others can build on them. All on github.com/meniData1.
EMNLP 2024
Data and evaluation code from our study comparing unsupervised fine-tuning against retrieval-augmented generation for injecting knowledge into LLMs, including facts a model never saw in pre-training.
2025
Datasets and scripts for continual pre-training from limited data using instructions: a cheaper way to teach a model new, long-tail knowledge without forgetting what it already knows.
2024
Training code for our ablation study on how multi-task fine-tuning "cocktails" change LLM performance in domain-specific settings like finance, across dozens of task combinations.
2024 · dataset
A gold-standard schema mapping between the MIMIC-III and OMOP medical data models, released as a benchmark for retrieval-enhanced schema matching with LLMs in healthcare.