Training an LLM to generate mathematical proofs with a formal verifier in Python

Code snippets for my 2025 lecture at Columbia University, an introduction to AI Agents

Personal website

Example of LLM generated Alloy code for deductive reasoning from English descriptions.

Slides, scripts and materials for the Machine Learning in Finance course at NYU Tandon, 2023.

A brief (and inaccurate) history of derivatives, with a brief (and incomplete) Python implementation

An end-to-end implementation of intent prediction with Metaflow and other cool tools

SessionPath is a deep learning model that provides personalized category suggestions for type-ahead APIs. This repo re-implements the original paper (https://arxiv.org/abs/2005.12781) leveraging Lu…

Joining the modern data stack with the modern ML stack

Recommendations at "Reasonable Scale": joining dataOps with recSys through dbt, Merlin and Metaflow

Playground for using large language models into the Modern Data Stack for entity matching

Personalization with deep learning in 100 lines of code

Playground for generating cards in the style of "Magic The Gathering" using generative AI

Materials for my 2021 NYU class on NLP and ML Systems (Master of Engineering).

Slides, scripts and materials for the Machine Learning in Finance Course at NYU Tandon, 2022

Python+node wrapper to read/send message from/to Anki Overdrive bluetooth vehicles.

Ingesting data with Pulumi, AWS lambdas and Snowflake in a scalable, fully replayable manner

Template-based generation of DAG cards from Metaflow classes, inspired by Google cards for machine learning models.

In-Session Personalization Workshop for eCommerce, April 2021, and the MICES Workshop in June 2021.

A PaaS End-to-End ML Setup with Metaflow, Serverless and SageMaker.

WIP code for the "on the plurality of graphs" paper

Generating meaningful perspectives with NLP and Probabilistic Programming.

Deploying a webppl probabilistic program as an (AWS lambda) endpoint.

Old-style computational semantics at the time of Python 3.6

Python micro-service to serve a decision tree trained with Spark through AWS Lambda

Serve a 1x1 GIF pixel from an AWS lambda-powered endpoint

Serve tensorflow models prediction from AWS lambda endpoints