Lead AI Platform Architect — Hybrid NC Contract

InfiCare; North Carolina; Hybrid; USD 165,000 - 331,000; Full time

Job summary

InfiCare is seeking an AI Architect in North Carolina (Hybrid: 3 days in office). This contract role requires 10+ years in software architecture, including 3 years building production-grade LLM/AI systems.

You will design multi-agent orchestration, MCP-based data/tool integration, and scalable AI platform infrastructure. The ideal candidate will lead architectural decisions, mentor engineers, and ensure low-latency, high-throughput delivery across enterprise environments.

Qualifications

• 10 years of software architecture experience, with 3 years hands-on in production LLM/AI systems.
• Experience with multi-agent frameworks and MCP protocols.
• Strong cloud and containerization expertise.

Responsibilities

• Design and implement multi-agent orchestration frameworks with autonomous negotiation, task delegation, and secure inter-agent communication.
• Architect and build scalable MCP servers and clients to connect LLMs to data sources, tools, and enterprise environments.
• Drive the architectural vision for an internal AI development platform with high throughput and low latency.
• Write production-ready code, prototypes, and establish dev practices for AI apps.
• Standardize architectural patterns; mentor junior engineers; communicate with non-technical stakeholders.

Skills

Multi-agent frameworks

MCP protocol

RAG pipelines

Prompt engineering

Python

TypeScript

Go

AWS

GCP

Azure

Kubernetes

Docker

LLM development

LangGraph

AutoGen

CrewAI

Tools

LangGraph

AutoGen

CrewAI

Job description

InfiCare is seeking an AI Architect in North Carolina (Hybrid: 3 days in office). This contract role requires 10+ years in software architecture, including 3 years building production-grade LLM/AI systems.

You will design multi-agent orchestration, MCP-based data/tool integration, and scalable AI platform infrastructure. The ideal candidate will lead architectural decisions, mentor engineers, and ensure low-latency, high-throughput delivery across enterprise environments.