View All Jobs 954

Software Engineer (ML Platform)

Enhance Ray Serve library to simplify development of next-gen ML applications in production.
San Francisco Bay Area
Mid-Level
$170,112 - 237,000 USD / year
2 months ago
Anyscale

Anyscale

Ray is the most popular open source framework for scaling and productionizing AI workloads.

✨ About The Role

- Develop a highly available service for ML model serving and enhance Ray Serve and other libraries to simplify the development of ML applications in production - Work on improving autoscaling capabilities to drive performance enhancements and cost savings - Optimize latency and throughput for both single- and multi-model serving scenarios - Collaborate with open-source users and customers to build and maintain world-class systems for serving ML models in production - Contribute directly to the Anyscale platform used by customers for critical applications

⚡ Requirements

- Experienced software engineer with a strong background in algorithms, data structures, and system design - Proficient in modern machine learning tooling such as PyTorch, TensorFlow, and JAX - At least 2+ years of relevant work experience in building and maintaining open-source projects or machine learning infrastructure in production - Skilled in developing highly available serving systems and optimizing latency and throughput for ML model serving - Ability to collaborate with diverse teams and customers, ranging from startups to industry-leading companies
+ Show Original Job Post
























Software Engineer (ML Platform)
San Francisco Bay Area
$170,112 - 237,000 USD / year
Software
About Anyscale
Ray is the most popular open source framework for scaling and productionizing AI workloads.