AWS Architect (Client: Penske)

AWS Architect (Client: Penske)Location: Reading PA (4-5 days onsite) Job DescriptionImplementation of Agents on Agentcore runtimeImplementation of SDLC for Agents (AIDLC) in AgentcoreUnderstanding of Strands or any other Agentic AI framework like Langraph, Langchain or Crew AIImplementation of Bedrock Knowledge BaseImplementation of Knowledge GraphImplementation of MCP serversImplementation of Agentcore GatewayImplementation of Agentcore IdentityImplementation of Agentic AI ObservabilityImplementation of Agentcore EvaluationsImplementation of AWS BedrockImplementation of AWS Bedrock Inference ProfileImplementation of AWS SagemakerAWS Services (Cloud) in GeneralTerraformJob ResponsibilitiesObservabilityAssess CloudWatch, X-Ray, Bedrock logging, AgentCore traces vs. agentic workflow requirements; produce gap analysis, Setup observability in DynatraceDesign 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 interactionsEvaluate LangFuse / LiteLLM proxy vs. AWS-native; deliver target-state observability architecture recommendationCost Tracking & TCOExtend tagging taxonomy to cover agent runtimes, MCP servers, vector DBs, Bedrock token consumption per namespaceDesign cost visibility model: aggregate agent, MCP, vector DB, and Bedrock token costs per team/departmentBuild CloudWatch (or equivalent) dashboards for per-team spend; configure AWS Budgets with alerting thresholdsAutomate cost reports delivered via email / Microsoft Teams; implement anomaly detection rulesMonitoring & AlertingDefine P1-P4 alerting rules: deployment failures, runtime errors, tool invocation failures, MCP connectivity issuesIntegrate alert notifications to Microsoft Teams channels and email; route by resource ownership tagsAuthor runbooks linked to every alert; publish in Confluence for developer self-service resolutionEvaluate AWS-native vs. third-party monitoring stack; deliver recommendation aligned to observability architectureSecurity & Access ControlAssess current IAM + tagging approach for multi-team isolation; identify scalability gaps and risksEvaluate Cedar policy engine (AgentCore) for fine-grained tool access control; document enterprise-scale gapsDesign scalable ABAC-based identity model for multi-team isolation without IAM policy sprawl; deliver Terraform modules

Create an account to see the full posting, access our search engine, and more.