Dr. Priya Narang

About

Applied ML researcher turning messy data into deployed models. I work on recommendation, forecasting, and the unglamorous MLOps that keeps them alive in production. PhD in ML, allergic to hype.

My PhD was on sequence models for healthcare time series — which taught me that the model is the easy part. The hard part is the data pipeline, the evaluation that doesn't lie to you, and the deployment that survives contact with reality. I've since built recommendation and forecasting systems serving millions of users, and I've learned to be deeply suspicious of any metric that only improves offline. I publish when the work is genuinely new, and I ship when it genuinely helps.

Experience

Applied ML across recommendation, forecasting, and healthcare — research to production

Selected Work

RecSys · Production · +7.2%

Two-tower ranking at scale

Rebuilt the recommendation ranker — +7.2% conversion, 40ms p99 at 3B daily candidates. Architecture + online eval.

OSS · Forecasting

forecast-kit (OSS)

A probabilistic forecasting library with proper backtesting built in. 1.8k stars.

Research · Healthcare

Clinical sequence models

PhD work: attention models for ICU time series. Published at NeurIPS workshop, code released.

MLOps · Evaluation

Eval you can trust

A framework for offline/online metric alignment that catches overfit before it ships.

Words

Recognition