Senior AWS AgentCore Platform Engineer

Halian | Managed Services, Recruitment Agency & Contract Staffing; Reading (Berks County); On-site; USD 140,000 - 190,000; Full time

Job summary

Halian | Managed Services is seeking a Senior AWS AgentCore Platform Engineer to design and scale an enterprise AI platform on Bedrock. You will own infrastructure, observability, security, and cost governance to enable multiple teams to build, deploy, and operate AI agents securely.

You will implement IAM/ABAC models, Terraform automation, CI/CD support, and integration with CloudWatch, Dynatrace, and other AWS services.

Qualifications

• 7+ years of AWS Cloud Engineering experience.
• 5+ years in DevOps, Platform Engineering, or SRE.
• Hands-on Terraform and AWS IAM experience.
• Experience with MLOps, Generative AI, or AI platform initiatives.
• Knowledge of Bedrock, AgentCore, and AWS observability tools.

Responsibilities

• Design and implement observability solutions across AWS AgentCore environments.
• Build distributed tracing and structured logging for AI agent workflows.
• Monitor LLM interactions, tool usage, MCP integrations, and agent execution paths.
• Evaluate and implement monitoring solutions including CloudWatch, Dynatrace, and AWS-native services.
• Develop deployment validation pipelines and operational health checks.
• Create and manage alerting strategies for platform and agent workloads.
• Define operational runbooks and troubleshooting procedures.
• Integrate monitoring alerts with Microsoft Teams and email notification systems.
• Improve platform reliability using SRE best practices.
• Build cost visibility and reporting frameworks for AI workloads.
• Monitor Bedrock token consumption and usage trends.
• Implement tagging strategies, AWS Budgets, and anomaly detection.
• Create dashboards showing AI platform spend by team and department.

Skills

Amazon Bedrock

AgentCore

Terraform

DevOps / SRE

AWS IAM

CloudWatch

MLOps

SageMaker

Observability & Monitoring

Infrastructure as Code

Job description

Are you passionate about building enterprise-scale AI platforms on AWS? We are seeking a Senior AWS AgentCore Platform Engineer to help strengthen and scale a next-generation AI Agent platform built on Amazon Bedrock AgentCore.

In this role, you will be responsible for designing and implementing the infrastructure, observability, security, monitoring, and cost governance capabilities that enable multiple teams to develop, deploy, and operate AI agents securely and efficiently.

What You'll Be Doing

AI Platform Observability & Reliability

• Design and implement observability solutions across AWS AgentCore environments.
• Build distributed tracing and structured logging for AI agent workflows.
• Monitor LLM interactions, tool usage, MCP integrations, and agent execution paths.
• Evaluate and implement monitoring solutions including CloudWatch, Dynatrace, and AWS-native services.
• Develop deployment validation pipelines and operational health checks.
• Create and manage alerting strategies for platform and agent workloads.
• Define operational runbooks and troubleshooting procedures.
• Integrate monitoring alerts with Microsoft Teams and email notification systems.
• Improve platform reliability using SRE best practices.
• Build cost visibility and reporting frameworks for AI workloads.
• Monitor Bedrock token consumption and usage trends.
• Implement tagging strategies, AWS Budgets, and anomaly detection.
• Create dashboards showing AI platform spend by team and department.

Security & Access Control

• Design scalable IAM and ABAC access control frameworks.
• Implement secure multi-team isolation models.
• Evaluate and deploy Cedar-based authorization strategies.
• Develop reusable Terraform modules for security and infrastructure automation.

Infrastructure Automation

• Build Infrastructure-as-Code solutions using Terraform.
• Automate provisioning and management of AgentCore, Bedrock, and AWS platform resources.
• Support CI/CD pipelines and platform engineering initiatives.

Required Skills

• Amazon Bedrock
• AgentCore (or AI/Agentic Platform Experience)
• Terraform
• DevOps / Site Reliability Engineering (SRE)
• AWS IAM
• CloudWatch
• MLOps
• SageMaker
• Observability & Monitoring
• Infrastructure as Code

Preferred Skills

• Dynatrace
• LangFuse
• LiteLLM
• Vector Databases
• CI/CD Automation

Required Experience

• 7+ years of AWS Cloud Engineering experience
• 5+ years working in DevOps, Platform Engineering, or SRE environments
• Experience supporting production cloud platforms at enterprise scale
• Hands-on experience with Terraform and AWS IAM
• Experience supporting MLOps, Generative AI, or AI platform initiatives