SRE for AI Inference Platform — Reliability & Automation

Alibaba Group; Bellevue (WA); On-site; USD 133,000 - 220,000; Full time

Benefits offered by this job

Medical Insurance

Dental Insurance

Vision Insurance

401(k) Plan

Basic Life Insurance

Wellbeing benefits like FSA

Up to 12 paid holidays

Up to 15 paid vacation days

Up to 72 hours paid sick time

Job summary

Alibaba Group's AI Inference Platform seeks a Site Reliability Engineer to deploy, operate, and maintain a high-availability model service platform, including initial construction and ongoing changes. You will optimize monitoring, respond to incidents, and build automation to ensure stability at scale.

Requirements: 3+ years in SRE/DevOps or backend, strong Linux/networking, cloud experience (Alibaba Cloud a plus), and programming in Python/Go/Java/C++.

Qualifications

• 3+ years of experience in SRE, DevOps, or backend development.
• Strong knowledge of distributed system operations.
• Fluency in Chinese and English for daily communication.
• Experience with cloud computing and Alibaba Cloud is a plus.
• Familiarity with MaaS or related concepts.

Responsibilities

• Oversee deployment, operation, and maintenance of the platform.
• Design monitoring metrics, log collection, and alerting strategies.
• Participate in emergency response and root cause analysis (RCA).
• Develop tools and scripts (Python/Go) to automate deployment, scaling, and fault recovery.
• Build automated diagnostic toolchains to accelerate issue resolution.

Skills

Python

Golang

Java

C++

Tools

Kubernetes

Prometheus

Istio

Calico

Job description

Alibaba Group's AI Inference Platform seeks a Site Reliability Engineer to deploy, operate, and maintain a high-availability model service platform, including initial construction and ongoing changes. You will optimize monitoring, respond to incidents, and build automation to ensure stability at scale.

Requirements: 3+ years in SRE/DevOps or backend, strong Linux/networking, cloud experience (Alibaba Cloud a plus), and programming in Python/Go/Java/C++.