Senior AWS AgentCore Platform Engineer/Architect IRC292142

GlobalLogic; Reading (Berks County); Hybrid; USD 130,000 - 140,000; Full time

Benefits offered by this job

Health insurance

401K with matching

Flexible spending accounts

Paid time off and holidays

Life and disability insurance

Job summary

GlobalLogic is seeking a Senior AWS AgentCore Platform Engineer/Architect to harden the AWS AgentCore platform for AI agent development and deployment. The role is based in Reading, PA with hybrid work (2-3 days in the office) and a salary range of $130,000–$140,000 base.

The candidate will drive observability, cost management and security controls across MCP servers, vector DBs, Bedrock usage, and tooling integration while collaborating with client teams to deliver scalable, fault-tolerant

Qualifications

• 10–15 years of software engineering with cloud infrastructure focus.
• Strong AWS services expertise including Bedrock, CloudTrail, CloudWatch and IAM.
• Hands-on Terraform and infrastructure-as-code experience.
• Experience designing cost tracking, budgeting and optimization on AWS.
• Knowledge of distributed tracing, structured logging and monitoring best practices.
• Ability to compare third-party versus native AWS observability solutions.
• Expertise in IAM, ABAC and fine-grained access control.

Responsibilities

• Establish observability with logging, tracing and dashboards; evaluate tools and design target-state architecture.
• Develop cost visibility and reporting with per-team cost dashboards and budgets.
• Define and implement monitoring and alerting across deployments; publish runbooks.
• Assess security and access controls; design scalable ABAC models and Terraform modules.

Skills

AWS

AWS Bedrock

AWS CloudTrail

AWS CloudWatch

AWS IAM

MCP

Python

Strands Agents

Terraform

Tools

Terraform

Job description

Senior AWS AgentCore Platform Engineer/Architect

Job ID: IRC292142

Designation: Senior Software Engineer

Function: Engineering

Experience: 10-15 years

Location: United States - San Jose, CA

Skills: AWS, AWS Bedrock, AWS CloudTrail, AWS CloudWatch, AWS IAM, MCP, Python, Strands Agents, Terraform

GlobalLogic estimates the starting pay range for this role to be performed hybrid in Reading, PA to be $130,000 to $140,000. This reflects base salary only and does not include additional performance‑linked variable compensation, benefits, etc.

Description

Role: Senior AWS AgentCore Platform Engineer

Location: Reading, PA (Hybrid 2-3 days a week from office)

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

Responsibilities

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

Qualifications

• 10-15 years of experience in software engineering with a focus on cloud infrastructure.
• Strong proficiency in AWS services including Bedrock, CloudTrail, CloudWatch, IAM, and observability tools.
• Hands-on experience with Terraform and infrastructure-as-code practices.
• Experience designing and implementing cost tracking, budgeting, and cost-optimization solutions on AWS.
• Knowledge of distributed tracing, structured logging, and monitoring best practices.
• Ability to evaluate and recommend third-party versus native AWS solutions for observability and monitoring.
• Expertise in IAM, ABAC, and fine-grained access-control policies.

Benefits

• Exciting projects across industry sectors.
• Collaborative environment with diverse, highly-talented teams.
• Work-life balance with flexible schedules and remote options.
• Professional development opportunities including education, certification, and training.
• Competitive benefits: health, life, short-term and long-term disability insurance, 401K with matching, flexible spending accounts, paid time off, and holidays.