Agentic AI

Intone Inc; Plano (TX); On-site; USD 90,000 - 130,000; Part time

Job summary

Intone Inc in Plano, TX is seeking an Agentic AI Engineer for a 6-month contract onsite to design, build, and deploy production-grade AI agents for enterprise environments.

You will orchestrate multi-agent workflows, implement RAG architectures with vector databases, and optimize LLM applications for production use.

Required: strong Python and Java, LangChain/LangGraph, tool calls, HITL, and scalable API/microservice experience delivering real business impact.

Qualifications

• Strong proficiency in Python and Java with hands-on experience developing and supporting production-grade applications.
• Experience building, deploying, and maintaining Agentic AI solutions in enterprise environments.
• Experience designing and orchestrating multi-agent workflows, tool integrations, and autonomous decision-making frameworks.
• Hands-on experience with LangChain and/or LangGraph.
• Experience with tool calling, ReAct frameworks, and Human-in-the-Loop (HITL) workflows.
• Experience designing and implementing RAG architectures and working with vector databases such as Pinecone, Milvus, or Weaviate.
• Experience with vLLM and LLM deployment/inference frameworks.
• Strong understanding of API development, microservices architectures, and integration patterns within modern software ecosystems.
• Ability to design, build, and deploy AI agents to production serving real users, with demonstrable business outcomes and adoption metrics.
• Understanding of scalability, reliability, observability, and enterprise architecture.
• Familiarity with responsible AI practices, model governance, security considerations, and enterprise development standards.

Responsibilities

• Design, build, and deploy AI agents into production environments serving real users.
• Develop and orchestrate multi-agent workflows, tool integrations, and autonomous decision-making frameworks.
• Develop, test, and optimize AI-driven applications that leverage large language models, agent frameworks, and retrieval capabilities.
• Design and implement RAG (Retrieval-Augmented Generation) architectures using vector databases.
• Implement agentic workflow patterns including tool calling, ReAct frameworks, and Human-in-the-Loop workflows.
• Troubleshoot, monitor, and support AI-enabled applications in production environments.
• Optimize latency, throughput, and inference costs for LLM applications.
• Implement guardrails and responsible AI practices to reduce hallucinations and unsafe outputs.
• Collaborate on enterprise architecture, scalability, reliability, and observability requirements.

Skills

Python

Java

Agentic AI

LangChain

LangGraph

ReAct frameworks

HITL workflows

RAG architectures

Vector databases

Pinecone

Milvus

Weaviate

LLM deployment

API development

Microservices

Observability

Security considerations

Tools

Pinecone

Milvus

Weaviate

Job description

This is a 6-month contract position based in Plano, Texas, working onsite. We are seeking an Agentic AI Engineer with hands-on experience building and deploying production-grade AI agents in enterprise environments.

Responsibilities

• Design, build, and deploy AI agents into production environments serving real users.
• Develop and orchestrate multi-agent workflows, tool integrations, and autonomous decision-making frameworks.
• Develop, test, and optimize AI-driven applications that leverage large language models, agent frameworks, and retrieval capabilities.
• Design and implement RAG (Retrieval-Augmented Generation) architectures using vector databases.
• Implement agentic workflow patterns including tool calling, ReAct frameworks, and Human-in-the-Loop workflows.
• Troubleshoot, monitor, and support AI-enabled applications in production environments.
• Optimize latency, throughput, and inference costs for LLM applications.
• Implement guardrails and responsible AI practices to reduce hallucinations and unsafe outputs.
• Collaborate on enterprise architecture, scalability, reliability, and observability requirements.

Qualifications

• Required
  • Strong proficiency in both Python and Java, with hands-on experience developing and supporting production-grade applications.
  • Demonstrated experience building, deploying, and maintaining Agentic AI solutions in enterprise environments.
  • Experience designing and orchestrating multi-agent workflows, tool integrations, and autonomous decision-making frameworks.
  • Hands-on experience with LangChain and/or LangGraph.
  • Experience with tool calling, ReAct frameworks, and Human-in-the-Loop (HITL) workflows.
  • Experience designing and implementing RAG architectures and working with vector databases such as Pinecone, Milvus, or Weaviate.
  • Experience with vLLM and LLM deployment/inference frameworks.
  • Strong understanding of API development, microservices architectures, and integration patterns within modern software ecosystems.
  • Ability to design, build, and deploy AI agents to production serving real users, with demonstrable business outcomes and adoption metrics.
  • Understanding of scalability, reliability, observability, and enterprise architecture.
  • Familiarity with responsible AI practices, model governance, security considerations, and enterprise development standards.