About The Role

We are seeking an AI Operations Engineer to ensure the reliability, governance, and adoption of AI solutions in China. This role focuses on MCP/API management, incident management for Copilot Studio, AI governance, and user enablement. You will not be responsible for active development this is a pure operations and governance role.

Key Responsibilities

MCP & API Management

Manage Model Context Protocol (MCP) interfaces ensuring reliable connections between AI tools and external data sources/APIs.

Oversee API services for the AI platform, including stability, security, and performance monitoring.
Configure and maintain context retrieval, grounding, and tool-calling patterns.

Copilot Studio Incident Management

Lead incident management for Copilot Studio environments, including triage, root cause analysis, resolution, and post-incident reporting.
Proactively monitor system health, implement improvements, and ensure high availability.
Establish and track SLAs for incident response and resolution.

Service Operations & Reporting

Generate service operation reports covering incidents, platform health, and API metrics.
Drive continuous improvement based on operational data.
Collaborate with development teams on RCA and preventive measures.

Requirements Experience

3+ years in AI operations, SRE, or platform operations roles.
Proven experience with Copilot Studio or similar conversational AI platforms.
MCP & API: Hands-on experience managing Model Context Protocol interfaces and API services.
Incident Management: Strong background in incident response, monitoring, alerting, SLA management, and post-mortems.
User Enablement: Excellent communication and training skills; ability to translate technical concepts into user-friendly guidance.
Language: Fluent English (written and verbal) required for global collaboration. Collaboration: Comfortable working with product, engineering, and business teams.