Devops Engineer

该职位来源于猎聘 Job Responsibilities：

• The DevOps engineers will be responsible for the daily operations, platform enhancements, and troubleshooting of the AI Platform &
  • Adoption, ensuring the high availability and performance of AI Gateway services. Stationed at the client office as a core member of the Managed Service team, collaborated closely with China Enterprise Technologies and global teams on solution design, delivery, and system reliability, adhering to strict SLAs.

• Oversee the engineering projects or epics, covering the AI Platform &
  • Adoption, Applications, and Use Cases (e.g. new MLops/AI gateway use cases) enhancement and development, facilitating communication, and ensuring that services and operations satisfy consumers. Also oversee the entire AI Platforms Architecture for various projects in client, to cater to business demands and solve business problems.

• Maintain and optimize the AI platforms daily operations, end-to-end monitoring, and ITIL process coverage (Incident, Problem, and Change Management following SOP/TOP guidelines).
• Drive DevOps and IaC practices by managing GitLab &
  • GitHub CI/CD pipelines, Kubernetes clusters, containerized deployments, and cloud infrastructure across AWS/Alibaba Cloud using IaC tools (Terraform, CDK, etc.).

• Support platform enhancements and API integrations, including microservices, REST API development, and IAM access controls (Ping Federation, AD, RBAC, etc.).
• Configure, monitor, and optimize AI Guardrail rules (input/output filtering, sensitive C3/C4 data classification, compliance checks, and audit logging) balancing security with user experience.
• Manage Model Context Protocol (MCP) Server lifecycles, configuration, org/workspace isolation, call volume monitoring, and technical integration support for business teams.
• Maintain comprehensive technical documentation (GitLab&GitHub MD, Confluence, Release Notes, SOPs/TOPs) and lead cross-regional technical communication and solution delivery with global teams in English.

  Qualifications &

  • Requirements:

• 5 years of IT DevOps experience.
• Excellent English reading and writing skills.
• Be familiar with Ali Guardrails technology.
• Lead engineer on solution design/delivery.
• Develop Frameworks for each code repo.
• Provide basic advisory services.
• Provide high-level consultancy for platform and use-case solutions design. Personal competency requirement from client：

AI adoption:

• Harness / Loop Engineering &
  • Human-in-the-Loop (HITL)

• GenAI / RAG / GraphRAG &
  • Vector Databases (e.g., Milvus, pgvector, Qdrant)

• Agentic Workflows &
  • Multi-Agent Orchestration

• Model Context Protocol (MCP) Server Integration &
  • Development

• AI Guardrails &
  • Compliance Engineering

• Use case observability & traceability analysis
• Prompt Engineering &
  • Systematic Model Evaluation Frameworks

• Structured Data/ Non-Structured Data Reporting
• Data Modeling (Knowledge Graph, Data Lake, Data Vault, Data Warehouse)
• Healthcare Expertise Knowledge and Communication

Project Management

• AI Platform Management and Backend Development:

AWS

AliCloud Infrastructure

• On-Premises Infrastructure

IaC

Kubernetes

• Database (i.e. PostgreSQL, MySql, Redshift)

Data Modeling

• Schedulers (i.e. Kubernetes, celery, SLURM)

MicroService and REST API

Executer Development