AI Engineer

Madison-Davis; United States; Remote; USD 120,000 - 180,000; Full time

Job summary

Madison-Davis, LLC is seeking an experienced AI Engineer to design and deploy enterprise Generative AI applications and automation solutions. You will build secure, production-ready AI agents and integrate AI capabilities into existing enterprise apps, collaborating with both technical and non-technical stakeholders.

The role emphasizes hands-on Python engineering, building RAG solutions, and connecting AI workflows with databases and SaaS platforms. Strong communication skills are essential.

Qualifications

• 5–8 years of engineering experience.
• At least 2 years of enterprise GenAI or LLM development experience.
• Strong Python engineering skills.
• Experience implementing AI agents and workflows.
• Experience with enterprise integrations and APIs.
• Knowledge of prompt engineering, AI architecture, and model evaluation.

Responsibilities

• Design and deploy enterprise Generative AI applications.
• Develop autonomous and human-supervised AI agents.
• Build custom MCP servers, tools, and integrations.
• Create RAG applications using enterprise information sources.
• Develop Python services and APIs supporting AI-powered workflows.
• Connect AI solutions with enterprise applications, databases, and SaaS platforms.
• Implement security controls, governance, and data privacy safeguards.
• Optimize production AI applications for reliability, scalability, and performance.

Skills

Python

GenAI/LLM development

AI agents

APIs & SaaS connectivity

Communication

Problem-solving

Education

Bachelor's degree in a relevant technical field

Tools

Claude Code

Anthropic APIs

Azure AI Foundry

Azure OpenAI Service

Azure AI Search

MCP server

Job description

An enterprise organization is looking for an experienced AI Engineer to develop and implement intelligent applications and automation solutions powered by Generative AI. This position is responsible for building secure, production-ready AI agents, integrating AI capabilities into existing enterprise applications, and creating retrieval-based solutions that help business teams work more effectively. The role involves significant hands-on Python engineering and collaboration with technical and nontechnical stakeholders.

RESPONSIBILITIES

• Design and deploy enterprise Generative AI applications.
• Develop autonomous and human-supervised AI agents.
• Build custom MCP servers, tools, and integrations.
• Create RAG applications using enterprise information sources.
• Develop Python services and APIs supporting AI-powered workflows.
• Connect AI solutions with enterprise applications, databases, and SaaS platforms.
• Implement security controls, model evaluation, governance, and data privacy safeguards.
• Optimize production AI applications for reliability, scalability, and performance.

ROLE REQUIREMENTS

• 5 8 years of relevant engineering experience.
• At least 2 years of enterprise GenAI or LLM development experience.
• Strong Python engineering skills.
• Practical AI agent and workflow implementation experience.
• Experience with custom tools, functions, and enterprise integrations.
• Understanding of APIs, databases, and SaaS connectivity.
• Knowledge of prompt engineering, AI application architecture, and model evaluation.
• Familiarity with RAG, vector databases, semantic search, and document retrieval.
• Understanding of AI security, governance, and privacy.
• Strong communication and problem-solving abilities.
• Bachelor's degree in a relevant technical field or equivalent experience.

PREFERRED EXPERIENCE

• Custom MCP server development.
• Claude Code, Anthropic APIs, or related agentic frameworks.
• Azure AI Foundry, Azure OpenAI Service, or Azure AI Search.
• Legal technology or professional-services experience.