AI Engineer Agentic AI / Generative AI

Job Description – AI Engineer

• Job Title: AI Engineer – Agentic AI / Generative AI

• Location: Louisville, KY

• Duration: 6 months

• Experience Required: 8–10 years

• Role: AI Engineer

• Essential Skill: AI Engineering

• Primary Focus: Agentic AI, RAG, MCP, Multi-Agent Orchestration, Python, LangChain, LangSmith, and Graph Databases

• Desirable Skill: Google Cloud Platform (GCP)

• Keyword: AI and Automation

Must-Have Technical Skills

• Strong experience in Agentic AI Full Stack development.

• Hands-on experience with Retrieval-Augmented Generation (RAG).

• Experience with Model Context Protocol (MCP).

• Strong experience in Multi-Agent orchestration.

• Experience with end-to-end AI solution deployment.

• Strong hands-on experience with LangChain.

• Experience with LangSmith.

• Strong Python programming skills.

• Experience with Graph Databases, such as:

  • Neo4j

  • Other graph database technologies

• Experience building scalable AI/GenAI applications from development through production deployment.

Good-to-Have Skills

• Google Cloud Platform (GCP) experience.

• Generative AI application development.

• AI/ML platform and cloud deployment experience.

• Experience with enterprise AI and automation solutions.

Roles & Responsibilities

• Design and develop Agentic AI full-stack solutions.

• Build production-ready RAG-based applications.

• Design and implement multi-agent architectures and orchestration frameworks.

• Implement MCP-based integrations for AI agents and tools.

• Develop AI applications using Python.

• Build conversational and intelligent applications using LangChain.

• Use LangSmith for LLM application development, tracing, evaluation, and monitoring.

• Design and implement graph-based solutions using Neo4j or similar graph databases.

• Develop AI solutions that integrate LLMs, enterprise data, APIs, tools, and external systems.

• Manage end-to-end deployment of AI applications from development through production.

• Design scalable and reliable AI application architectures.

• Integrate RAG pipelines with enterprise knowledge sources and data repositories.

• Develop agent workflows capable of reasoning, tool usage, task execution, and multi-agent collaboration.

• Troubleshoot and optimize AI application performance, reliability, and scalability.

• Collaborate with engineering and business teams to translate requirements into AI-driven solutions.

• Follow software engineering, testing, deployment, and monitoring best practices.

• Leverage GCP for AI application development and deployment where applicable.

Key Skills / Keywords

• Agentic AI

• Generative AI

• AI Engineering

• AI Automation

• RAG

• Retrieval-Augmented Generation

• MCP

• Model Context Protocol

• Multi-Agent Systems

• Multi-Agent Orchestration

• LangChain

• LangSmith

• Python

• Neo4j

• Graph Database

• LLM

• LLM Application Development

• AI Full Stack

• End-to-End Deployment

• GCP

• Google Cloud

• AI Architecture

• AI/ML Integration