AWS Platform Architect – Agentcore IRC298869

About the role

Work with the Client team to harden the new AWS AgentCore platform so it can be used by teams to develop and deploy AI agents.

Responsibilities

• Assess CloudWatch, X-Ray, Bedrock logging, and AgentCore traces against agentic workflow requirements; produce gap analysis
• Set up observability in Dynatrace
• Design post-deployment validation pipeline for agents and MCP servers (deployment health + tool registration checks)
• Implement distributed tracing and structured logging: LLM decisions, tool selections, sub-agent calls, MCP interactions
• Evaluate LangFuse / LiteLLM proxy vs. AWS-native options; deliver target-state observability architecture recommendation
• Extend tagging taxonomy to cover agent runtimes, MCP servers, vector DBs, and Bedrock token consumption per namespace
• Design cost visibility model that aggregates 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
• 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
• 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

Requirements

• Implementation of Agents on AgentCore runtime
• Implementation of SDLC for Agents (AIDLC) in AgentCore
• Understanding of Strands or any other Agentic AI framework like LangGraph, LangChain, or Crew AI
• Implementation of Bedrock Knowledge Base
• Implementation of Knowledge Graph & MCP servers
• Implementation of AgentCore Gateway & AgentCore Identity
• Implementation of Agentic AI Observability & Agentcore Evaluations
• Implementation of AWS Bedrock & AWS Bedrock Inference Profile
• Implementation of AWS Sagemaker
• General AWS Services (Cloud) and Terraform

Pay

GlobalLogic estimates the starting pay range for this role performed in Reading, PA is $180,000 to $200,000 and reflects base salary only. The amount offered may be higher or lower and is based on candidate qualifications, work experience, operational needs, travel and onsite requirements, internal peer equity, prevailing wage, responsibilities, and other market and business considerations.

Benefits

• Exciting projects with clients across industries using the latest technologies
• Collaborative environment with diverse teams in open, laid-back settings or global centers
• Flexible work schedules and work-from-home opportunities
• Continuing education classes, professional certification and training (technical, soft skills, language, communication)
• Competitive salaries, health and life insurance, short-term and long-term disability insurance, matched 401K, flexible spending accounts, PTO and holidays