DevOps Engineer - AI Runtime Services

📋 Description

• The LLM gateway: keys, routing, rate limits, failover
• Reliability: SLOs, on-call, incident postmortems
• Cost control: per-team/per-model budgets and quotas
• LLM observability: traces, prompts, ingest and billing visibility
• Evals and experimentation infra: harnesses, datasets, scoring plumbing
• Caching and guardrails: caching, safety, PII handling

🎯 Requirements

• Strong production infra background: Kubernetes, AWS, Terraform, GitOps
• Python proficiency; own services and tooling, not just scripting
• Real on-call and incident-response experience
• Observability fluency: instrument systems, chase cost/cardinality, alerting
• Hands-on with LLM systems: built agents or a RAG pipeline; used evals

🎁 Benefits

• Group Medical, Personal Accident, and Term Life Insurance
• Dental, vision, and OPD coverage
• Mental health support
• Fitness benefit
• Car lease policy
• Gratuity for long-term financial well-being