Responsibilities
Set up dashboards/alerts; script repetitive ticket steps.
Participate in RCAs; log user pain points weekly; propose product fixes.
Build a lightweight agent (e.g., telegram bot) with at least one reusable skill (log fetch, health check, etc.).
Optimize a small workflow in incident management tooling.
Must-have
CS/Data/AI or related major; Linux + scripting (Shell/Python); basic SQL.
Write actionable runbooks.
Improve user experience from support data.
Basic understanding of agents and skills.
Nice-to-have
K8s, CI/CD, Terraform. MLOps project experience. Built a simple LLM agent or defined skills (LangChain, function calling). TSM tool experience.