Senior Data Scientist · American Express

Building useful AI for the real world.
With a bias toward clarity.

I work on recommender systems, sequence modeling, foundation models, and reliable evaluation. This is my corner of the internet for things I build, learn, and share.

CURRENT FOCUS
Systems that learnfrom profiles, events, and feedback
Research → practiceturning ideas into usable tools
01 · THE SHORT VERSION

A practical research mindset.

I like the space between a paper and a product: understanding how a method works, implementing it carefully, then finding where it creates real value.

01

Personalization

Recommender systems and sequence models for better experiences at scale.

02

Foundation models

Tools and abstractions that make profile and event data useful for modern ML.

03

Reliable evaluation

Measuring what actually improves an AI system—not just what looks impressive.

02 · SELECTED WORK

Things I’ve shipped.

Open-source experiments and tools built to make research easier to use.

fastpragma

A Python API for PRAGMA-style foundation models—from tokenization and pretraining to embeddings and fine-tuning.

llm-rsa

Recursive Self-Aggregation for LLMs: sample and synthesize candidate answers into a stronger response.

03 · A NOTE

“The best work sits where curiosity meets usefulness. I’m still learning, building, and writing my way there.” — Risheekkumar