Job Description:

- Build and maintain reliable infrastructure for AI agent deployments.

- Manage production AI workloads across Kubernetes and cloud platforms.

- Design monitoring and alerting for AI agents, LLM applications, and distributed systems.

- Implement SRE best practices including SLI, SLO, SLA, incident management, and postmortem analysis.

- Automate deployment pipelines using CI/CD tools.

- Manage AI model lifecycle, deployment, rollback, and performance monitoring.

- Optimize GPU utilization and AI infrastructure costs.

- Troubleshoot production issues involving AI agents, APIs, Kubernetes, networking, and cloud services.

- Implement observability using logs, metrics, traces, and dashboards.

- Develop automation scripts for infrastructure provisioning and operational tasks.

- Collaborate with AI/ML engineers, platform teams, and software developers.

- Ensure security, compliance, and governance for AI systems.

- Support production releases and participate in on-call rotations.

📌 AI Agentic ops SRE (Bengaluru)
🏢 Acme Services Private
📍 Bengaluru