- Hyderabad, Telangana, India
- On-site
- Full-time · Mid
- 4–7 years
Support Engineer role focused on AI platforms, managing Kubernetes, cloud deployments, and LLM routing.
Responsibilities
- Own Severity 2–4 cases end to end and support Severity 1 incidents: triage, reproduce, find root cause, fix.
- Troubleshoot Kubernetes and cloud deployments, LLM routing and provider issues, RAG quality and agent behavior.
- Debug Admin Portal (FinOps, token allowances, governance, SSO) and MCP integration issues.
- Help customers with upgrades and patches, file clear bug reports, and write RCAs and KB articles.
Requirements
- Nice to have: CKA
- Nice to have: CKAD
- Nice to have: SOC 2
- Nice to have: HIPAA
- Nice to have: vector databases