📍 Local Job Near You
Staff Machine Learning Engineer, ML Infrastructure - Online
Unity Technologies
📍
Shanghai, China
Location
Shanghai
Posted
June 15, 2026
Commute
Local Area
Local Opportunity Near You!
This job is in your area. Enjoy a short commute and work close to home.
Job Description
**Shanghai, China**
**Staff Machine Learning Engineer, ML Infrastructure - Online**
Location
Shanghai, China
Department
AI & Machine Learning
Requisition ID
JOBREQ-2616113
**Role description**
**The opportunity**
Unity Vector builds ML infrastructure that powers real-time prediction, experimentation, attribution, and AI-driven decision-making across the company.
Our online ML systems serve production models at scale, supporting low-latency inference, large-scale experimentation, model deployment and optimization, feature processing, and business-critical decisioning. As model complexity, traffic volume, and experimentation velocity continue to grow, our inference platform must remain reliable, scalable, observable, and cost-efficient.
To support this growth, we need strong technical ownership to evolve the online ML infrastructure that enables ML teams to safely deploy, validate, and operate production models at scale.
**Staff Machine Learning Engineer, ML Infrastructure - Online**
Location
Shanghai, China
Department
AI & Machine Learning
Requisition ID
JOBREQ-2616113
**Role description**
**The opportunity**
Unity Vector builds ML infrastructure that powers real-time prediction, experimentation, attribution, and AI-driven decision-making across the company.
Our online ML systems serve production models at scale, supporting low-latency inference, large-scale experimentation, model deployment and optimization, feature processing, and business-critical decisioning. As model complexity, traffic volume, and experimentation velocity continue to grow, our inference platform must remain reliable, scalable, observable, and cost-efficient.
To support this growth, we need strong technical ownership to evolve the online ML infrastructure that enables ML teams to safely deploy, validate, and operate production models at scale.