Selected work

Things (hopefully) worth showing.

I'm Founder and CTO of Enderis. Before that, I co-founded Simply-Useful and worked on applied AI research at Microsoft. Here's some of that work.

building now

Founder and CTO · Enderis

Enderis

An agent can refuse a refund, make an exception, or escalate it. Knowing which is right depends on the business. Enderis helps the people building an agent and the people responsible for its work agree on that behavior. Run the real agent in simulated systems, inspect its decisions and what it changed, then define what should happen. Those expectations become executable product specs that teams can rerun whenever the agent, workflow, or policy changes.

simulate the system · inspect behavior · specify expectations · verify changes

Visit enderis.ai

shipped · still live

co-founder & technical lead · oct 2025 – june 2026

Simply-Useful

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

App Store Google Play Web app simply-useful.com →

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

Fine-Tuning or Retrieval?

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.

GitHub arXiv ACL Anthology

2025

Knowledge-Instruct

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.

GitHub arXiv

2024

The Cocktail Effect

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.

GitHub arXiv

2024 · dataset

ReMatch: MIMIC to OMOP

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.

GitHub arXiv