Software Engineer - Model Serving Infrastructure

Anyscale(1 month ago)

RemoteFull TimeJunior$89,478 - $118,619 (estimated)Engineering

About this role

A Software Engineer - Model Serving Infrastructure at Anyscale is responsible for developing high-performance systems for serving machine learning models in production. This role involves enhancing the Ray Serve library, optimizing latency and throughput, and improving autoscaling capabilities for complex ML applications. The engineer collaborates with both open-source users and industry clients like Uber and Shopify to ensure seamless deployment and operational efficiency across diverse machine learning environments.

View Original Listing

Required Skills

ML Model Serving
Ray Serve
Performance Optimization
Autoscaling
Systems Design
Algorithms
Data Structures
PyTorch
TensorFlow
JAX

+3 more

About Anyscale

www.anyscale.com

Anyscale is a cutting-edge platform designed for building and running AI applications with scalability and efficiency at its core. Powered by Ray, it enables AI developers to seamlessly manage all machine learning (ML) and artificial intelligence (AI) workloads, whether in the cloud or on-premises. Anyscale focuses on simplifying the complexities of deploying various workloads, from data processing to training and inference, ultimately facilitating faster development and operational reliability. The platform is particularly favored by organizations seeking to optimize their ML workflows while leveraging the expertise of the original creators of the Ray framework.