Senior AWS Infrastructure Engineer AI/LLM Observability

Senior DevOps Engineer responsible for building and operating AWS cloud infrastructure, CI/CD pipelines, automation, and observability capabilities for secure, reliable, and scalable platforms. The role has a strong focus on AWS infrastructure (80%), observability, telemetry, security, RCA, and AI/LLM monitoring.

Key Responsibilities:

• Design, build, and maintain AWS infrastructure and CI/CD pipelines.
• Manage infrastructure as code using Terraform.
• Implement end-to-end observability, monitoring, telemetry, and traceability.
• Leverage AWS CloudWatch and modern observability platforms for monitoring and alerting.
• Perform Root Cause Analysis (RCA) and support incident/reliability engineering.
• Implement security telemetry, DevSecOps, governance, and compliance automation.
• Design observability capabilities for AI agents, LLM applications, and AI-enabled platforms.
• Support LLM/AI observability, model monitoring, and agent telemetry.
• Partner with engineering teams on production readiness, resiliency, and operational excellence.

Key Skills:

• AWS Infrastructure 80% Focus
• Terraform / Infrastructure as Code
• CI/CD Pipelines
• CloudWatch
• Observability & Traceability
• Telemetry & Monitoring
• Root Cause Analysis (RCA)
• DevSecOps / Security Telemetry
• AI Agent & LLM Observability
• Cloud Automation
• Distributed Systems / APIs
• Python / Bash / PowerShell