PoplarML

Deploy Machine Learning Models with One Command

Y CombinatorWinter 2023ActiveB2BEngineering, Product and DesignAIOpsArtificial IntelligenceMachine LearningB2B

What they do

Problem

Teams struggle to deploy machine learning models to scalable GPU infrastructure as reliable API endpoints quickly and easily.

Solution

PoplarML provides a one-command platform to deploy any ML model to a fleet of GPUs as a ready-to-use, scalable API endpoint.

Who it's for

Machine learning engineers and developers at companies that need to serve ML models via GPU-backed APIs.

Danna Liu

Founder

Co-Founder of PoplarML, Previously Research @ Snap, SWE @ Stripe, Coinbase, Microsoft, PagerDuty

Evan Chu

Founder

Co-Founder @ PoplarML. Previously SWE @ Stripe, Amazon, AWS