AWS Architect

Kutir Technologies; Reading (Berks County); On-site; USD 140,000 - 170,000; Full time

Job summary

Kutir Technologies is seeking an AWS Architect to lead cloud architecture and observability across Bedrock services. The role focuses on implementing reliable agent-based runtimes, monitoring, and cost-aware design in a primarily AWS-based environment.

The position requires expertise in AWS services, including Bedrock, Sagemaker, and Infra tooling, with an emphasis on scalable IAM, ABAC, and observability. Onsite presence in Reading, PA is expected.

Responsibilities

• Observe cloud deployments with CloudWatch, X-Ray, and Bedrock logging; produce gap analyses.
• Design post-deployment validation for agents and MCP servers; health checks.
• Implement distributed tracing and structured logging for decisions, tool calls, and MCP interactions.
• Evaluate monitoring stacks and propose an observability architecture aligned to requirements.

Skills

AWS architecture

Observability

Terraform

Security & IAM

Cost optimization

Tools

AWS Bedrock

Langchain/Langraph

Dynatrace

CloudWatch/X-Ray

Terraform

Job description

Title: AWS Architect
Location: Reading PA (4-5 days onsite)

Job Description

• 1. Implementation of Agents on Agentcore runtime
• 2. Implementation of SDLC for Agents (AIDLC) in Agentcore
• 3. Understanding of Strands or any other Agentic AI framework like Langraph, Langchain or Crew AI
• 4. Implementation of Bedrock Knowledge Base
• 5. Implementation of Knowledge Graph
• 6. Implementation of MCP servers
• 7. Implementation of Agentcore Gateway
• 8. Implementation of Agentcore Identity
• 9. Implementation of Agentic AI Observability
• 10. Implementation of Agentcore Evaluations
• 11. Implementation of AWS Bedrock
• 12. Implementation of AWS Bedrock Inference Profile
• 13. Implementation of AWS Sagemaker
• 14. AWS Services (Cloud) in General
• 15. Terraform

Job Responsibilities

• 1. Observability
  Assess CloudWatch, X-Ray, Bedrock logging, AgentCore traces vs. agentic workflow requirements; produce gap analysis, Setup observability in Dynatrace
  Design post-deployment validation pipeline for agents & MCP servers (deployment health + tool registration checks)
  Implement distributed tracing & structured logging: LLM decisions, tool selections, sub-agent calls, MCP interactions
  Evaluate LangFuse / LiteLLM proxy vs. AWS-native; deliver target-state observability architecture recommendation
• 2. Cost Tracking & TCO
  Extend tagging taxonomy to cover agent runtimes, MCP servers, vector DBs, Bedrock token consumption per namespace Design cost visibility model: aggregate agent, MCP, vector DB, and Bedrock token costs per team/department
  Build CloudWatch (or equivalent) dashboards for per-team spend; configure AWS Budgets with alerting thresholds
  Automate cost reports delivered via email / Microsoft Teams; implement anomaly detection rules
• 3. Monitoring & Alerting
  Define P1 P4 alerting rules: deployment failures, runtime errors, tool invocation failures, MCP connectivity issues
  Integrate alert notifications to Microsoft Teams channels and email; route by resource ownership tags
  Author runbooks linked to every alert; publish in Confluence for developer self-service resolution
  Evaluate AWS-native vs. third-party monitoring stack; deliver recommendation aligned to observability architecture
• 4. Security & Access Control
  Assess current IAM + tagging approach for multi-team isolation; identify scalability gaps and risks
  Evaluate Cedar policy engine (AgentCore) for fine-grained tool access control; document enterprise-scale gaps
  Design scalable ABAC-based identity model for multi-team isolation without IAM policy sprawl; deliver Terraform modules