Senior AI Platform SRE — Reliability & Scale

Schonfeld; Hong Kong; On-site; HKD 900,000 - 1,300,000; Full time

Job summary

You will define reliability standards, own observability, incident response, and the scalability of our AI platform, ensuring high availability of agents, gateways, LLM proxies, and RAG pipelines. You’ll also contribute to code quality and best practices, helping developers build with the platform while communicating effectively with stakeholders.

Qualifications

• 5+ years in cloud automation or SRE-like role.
• Proficient in Python and REST APIs.
• Experience with relational and NoSQL databases.
• Hands-on with AWS, Kubernetes, and CI/CD pipelines.
• Interest in AI and issue-solving for production systems.

Responsibilities

• Define SLOs, error budgets, and incident runbooks.
• Own observability, incident response, reliability, and scalability of the AI platform.
• Ensure high availability of agents, gateways, LLM proxies, and RAG pipelines.
• Support users via a dedicated help channel and root-cause investigations.
• Improve code quality and development lifecycles for the platform.

Skills

Cloud automation

Site Reliability Engineering

Python

REST APIs

Event-driven architectures

PostgreSQL

MySQL

DynamoDB

ElasticSearch

OpenSearch

AWS

Kubernetes

GitHub Actions

CI/CD pipelines

Observability (DataDog)

AI enthusiasm

Strong communication

Agentic AI / RAG pipelines

MCP servers

Job description

You will define reliability standards, own observability, incident response, and the scalability of our AI platform, ensuring high availability of agents, gateways, LLM proxies, and RAG pipelines. You’ll also contribute to code quality and best practices, helping developers build with the platform while communicating effectively with stakeholders.