Principal Solution Architect – Agentic AI

HeartCentrix Solutions; United States; On-site; USD 180,000 - 260,000; Full time

Job summary

HeartCentrix Solutions seeks a seasoned Architect to define and drive the technical architecture for an enterprise-scale agentic AI platform. This hands-on role requires real-world AI/LLM production experience and collaboration with ML and software engineers to ensure scalable, secure, and reliable systems.

You will define API contracts, data flows, and standards across the platform, mentor engineers, and stay current with emerging AI tech to guide platform evolution.

Qualifications

• 10+ years of software architecture/engineering experience.
• Hands-on experience with LLM orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, or similar.
• Production experience building and deploying agentic AI or LLM-powered applications at scale.
• Strong distributed systems and microservices architecture experience.
• Strong API design experience, including REST and/or gRPC.
• Experience with at least one additional language such as Java, Go, or TypeScript.
• Strong understanding of event‑driven architecture and distributed systems.
• Experience with prompt engineering, tool‑use patterns, RAG pipelines, and AI agent reliability/observability.

Responsibilities

• Define and evolve the architecture for multi-agent systems, LLM orchestration, and AI platform services.
• Design frameworks and patterns for agent orchestration, tool use, LLM integration, and workflow execution.
• Establish best practices around reliability, observability, security, guardrails, and scalability for production AI systems.
• Lead technical design reviews and document key architecture decisions through ADRs.
• Define API contracts, data flows, integration patterns, and technical standards across the AI platform.
• Work closely with ML and software engineers to ensure scalable, secure, maintainable, production-ready solutions.
• Evaluate emerging agentic AI frameworks such as LangGraph, CrewAI, Semantic Kernel, AutoGen, and similar technologies.
• Design and review solutions involving LLM routing, prompt engineering, RAG, tool use, and multi-agent workflows.
• Help establish standards for monitoring, evaluation, and reliability of AI agents.
• Mentor engineers and provide guidance on building production‑grade AI applications.
• Stay current on emerging AI technologies and determine which ones are worth bringing into the platform.
• Be hands‑on when needed, including prototyping and validating architectural approaches through code.

Skills

LLM orchestration

Distributed systems

API design

REST/gRPC

Programming languages

Event-driven architecture

Prompt engineering

Tools

LangChain

LangGraph

Semantic Kernel

AutoGen

Job description

We’re looking for a seasoned Architect to help define and drive the technical architecture behind an enterprise-scale agentic AI platform. This is a hands‑on architecture role for someone who has actually built and deployed AI/LLM systems in production — not just experimented with prototypes.

You’ll work closely with ML engineers, software engineers, and other architects to design scalable, secure, reliable AI systems and establish the technical standards that teams will use across the platform.

What You’ll Be Doing

• Define and evolve the architecture for multi-agent systems, LLM orchestration, and AI platform services.
• Design frameworks and patterns for agent orchestration, tool use, LLM integration, and workflow execution.
• Establish best practices around reliability, observability, security, guardrails, and scalability for production AI systems.
• Lead technical design reviews and document key architecture decisions through ADRs.
• Define API contracts, data flows, integration patterns, and technical standards across the AI platform.
• Work closely with ML and software engineers to make sure solutions are scalable, secure, maintainable, and production-ready.
• Evaluate emerging agentic AI frameworks such as LangGraph, CrewAI, Semantic Kernel, AutoGen, and similar technologies.
• Design and review solutions involving LLM routing, prompt engineering, RAG, tool use, and multi-agent workflows.
• Help establish standards for monitoring, evaluation, and reliability of AI agents.
• Mentor engineers and provide guidance on building production‑grade AI applications.
• Stay current on emerging AI technologies and determine which ones are worth bringing into the platform.
• Be hands‑on when needed, including prototyping and validating architectural approaches through code.

Must-Have Skills

• 10+ years of software architecture/engineering experience.
• Hands‑on experience with LLM orchestration frameworks such as LangChain, LangGraph, Semantic Kernel, or similar.
• Production experience building and deploying agentic AI or LLM-powered applications at scale.
• Strong distributed systems and microservices architecture experience.
• Strong API design experience, including REST and/or gRPC.
• Experience with at least one additional language such as Java, Go, or TypeScript.
• Strong understanding of event‑driven architecture and distributed systems.
• Experience with prompt engineering, tool‑use patterns, RAG pipelines, and AI agent reliability/observability.

Nice to Have

• Kubernetes or other container orchestration experience.
• MLOps or LLMOps experience.
• Vector databases such as Pinecone, Weaviate, or pgvector.
• Knowledge graphs.
• AI agent evaluation, benchmarking, or testing frameworks.
• Airline or travel industry experience.
• TOGAF or similar architecture certification.