Senior Generative AI Architect – Agentic Systems

Capgemini; St. Louis (MO); On-site; USD 44,579 - 69,651; Full time

Benefits offered by this job

Medical benefits

Dental benefits

Retirement benefits

Job summary

LangGraph in St. Louis, MO is seeking a Senior Generative AI Developer to lead the design, development, and deployment of production-grade AI agents.

You will leverage AWS Bedrock AgentCore and Kiro tools to build scalable, secure multi-agent systems with advanced A2A communication. Responsibilities include designing agent systems, enabling supervisor/sub-agent handoffs, and integrating MCP-based protocols while maintaining secure IAM practices.

Qualifications

• Senior-level developer to lead design, development and deployment of production-grade AI agents.
• Expertise with AWS Bedrock, AgentCore Runtime, and Kiro toolchain.
• Strong background in multi-agent systems and A2A collaboration patterns.
• Experience implementing secure, scalable cloud architectures and agile practices.

Responsibilities

• Design scalable agent systems using Bedrock AgentCore Runtime and Gateway.
• Implement robust Agent-to-Agent communication and supervisor/sub-agent handoffs.
• Optimize IDE workflows with Kiro IDE and Kiro Powers for production code.
• Integrate external resources via Model Context Protocol (MCP).
• Manage stateful agent sessions with AgentCore memory modules.
• Enforce deterministic IAM security for secure microVM environments.

Skills

AWS Bedrock

AgentCore Runtime

Kiro

Multi-Agent Orchestration

MCP Protocols

Python/TypeScript

Agile methodologies

JIRA

Chalkpages

Tools

AWS Bedrock

AgentCore Runtime

Gateway

Memory

Identity

Observability

Kiro IDE

Kiro Powers

JIRA

Chalkpages

Job description

LangGraph in St. Louis, MO is seeking a Senior Generative AI Developer to lead the design, development, and deployment of production-grade AI agents.

You will leverage AWS Bedrock AgentCore and Kiro tools to build scalable, secure multi-agent systems with advanced A2A communication. Responsibilities include designing agent systems, enabling supervisor/sub-agent handoffs, and integrating MCP-based protocols while maintaining secure IAM practices.