Position: Senior AWS DevOps / Platform Engineer (Agentic AI Infrastructure)
Location: Hybrid (Pan-India)
About the Client & Role Context
Our client is advancing its digital transformation by operationalizing next-generation Agentic AI and Autonomous Workflows. Moving beyond basic LLM wrappers, they are deploying production-ready AI agents integrated deep within enterprise cloud backends.
We are seeking a hands-on Senior AWS DevOps / Platform Engineer who will own the execution pipeline to transition Agentic AI workloads from Proof-of-Concept (POC) into secure, scalable, and observable AWS production environments. This is a pure build-and-run engineering role focused on high reliability and cloud economics.
Core Responsibilities
* Build, secure, and operate DEV, TEST, and PROD AWS cloud environments dedicated to Agentic AI and Python microservices.
* Containerize agentic AI systems using Docker, Amazon EKS/ECS, and Amazon Bedrock AgentCore.
* Define and maintain infrastructure-as-code using Terraform, enforcing zero-trust networking, IAM workload identities, and KMS key management.
* Design DevSecOps CI/CD pipelines incorporating static code analysis, vulnerability scanning, continuous integration, and dynamic AI evaluation/guardrail gates.
* Implement end-to-end telemetry utilizing OpenTelemetry (ADOT), Amazon CloudWatch, and distributed tracing across agent sessions.
* Establish SRE practices including Service Level Objectives (SLOs), automated failure domain isolations, and root-cause analysis (RCA) frameworks.
* Apply FinOps practices to optimize AWS resource utilization, token consumption costs, and container execution performance.
Required Qualifications & Experience
* 6+ years of hands-on experience in AWS Platform Engineering, DevOps, or Site Reliability Engineering.
* Demonstrated experience delivering containerized Python/Node applications into live AWS production.
* Direct production exposure to Amazon Bedrock and/or Bedrock AgentCore frameworks.
* Deep technical expertise in Kubernetes (EKS), Docker, and Terraform IaC.
* Advanced pipeline automation skills using GitHub Actions, GitLab CI, or Jenkins with integrated DevSecOps scanning.
* Strong proficiency in OpenTelemetry (ADOT) or enterprise APM tools for distributed tracing.
* Practical automation skills using Python and Bash scripting.
* Strong grasp of FinOps principles within AWS cloud ecosystems.
Preferred Qualifications
* Experience with GitOps (ArgoCD / Helm), AgentOps, or MCP tool integrations.
* Working knowledge of multi-account AWS architectures (Control Tower, AWS Organizations).
* Certifications: AWS Certified DevOps Engineer - Professional or AWS Certified Solutions Architect - Professional.