Description

You will own the platform engineering, DevOps, and SRE responsibilities for the AgentCore ecosystem, ensuring robust infrastructure and observability for AI-driven applications.

This role is hybrid.

Responsibilities

• Design and maintain AWS infrastructure using Terraform, focusing on IAM, CloudWatch, Lambda, and Bedrock services.
• Implement and manage observability stacks using Dynatrace, Jaeger, or Honeycomb to support distributed tracing and agent lifecycle monitoring.
• Build and optimize CI/CD pipelines to support the deployment of Agents on the AgentCore runtime and Agentic SDLC workflows.
• Collaborate in an Agile environment to integrate tools like Microsoft Teams and Confluence, ensuring seamless development and deployment cycles.
• Apply familiarity with LLM lifecycles, including prompt execution, token usage, and frameworks such as LangChain or AgentCore.

Required Skills

• 8+ years of experience in Platform Engineering, DevOps, or Site Reliability Engineering (SRE).
• Deep proficiency in AWS services, specifically IAM, CloudWatch, Bedrock, and Lambda.
• Advanced experience with Terraform for infrastructure as code.
• Proven experience with observability tools (Dynatrace, Jaeger, or Honeycomb) and distributed tracing standards.
• Strong background in CI/CD pipeline design and automation.
• Familiarity with LLM frameworks such as LangChain, LangGraph, or Crew AI.
• Experience implementing Agents on AgentCore runtime, including Gateway, Identity, and Knowledge Base integrations.
• Knowledge of Agentic AI observability, evaluations, and inference profiles.

Preferred Skills

• Experience implementing MCP servers, Knowledge Graphs, or Strands within the AgentCore ecosystem.
• Hands-on experience with AWS SageMaker and Bedrock Inference Profiles.

Key Skills

Education

Any Graduate