AI Engineer on Chicago

Confiar Services; Chicago (IL); On-site; USD 120,000 - 180,000; Full time

Job summary

Confiar Services in the United States is seeking experienced AI Engineers to design, develop, and deploy AI-powered applications leveraging LangChain, LangGraph, LLMs, and RAG. You will build scalable workflows and integrate with enterprise data and APIs to deliver production-grade AI solutions.

Ideal candidates will have hands-on experience with Azure AI Foundry and strong problem-solving, collaboration, and communication skills to work with cross-functional teams toward reliable,

Qualifications

• Hands-on experience building LLM-powered apps.
• Strong understanding of enterprise AI architectures.
• Experience with prompt engineering and context management.
• Ability to integrate AI components with APIs and data sources.

Responsibilities

• Design, develop, and implement AI-powered applications using LLMs.
• Build AI workflows and agent-based solutions with LangChain and LangGraph.
• Design RAG architectures to enhance LLM responses with enterprise data.
• Develop, integrate, and deploy AI solutions using Azure AI Foundry.
• Integrate LLMs with enterprise systems, APIs, and data sources.
• Optimize AI applications for performance and reliability.
• Troubleshoot, test, and improve AI models and workflows.
• Collaborate with cross-functional teams to deliver production-ready AI solutions.

Skills

LangChain

LangGraph

LLMs

RAG

Azure AI Foundry

Job description

Location: Edina, MN (Primary) / Chicago, IL

Job Summary

We are urgently looking for highly skilled, hands-on AI Engineers with strong experience in LangChain, LangGraph, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and Azure AI Foundry. The ideal candidates will have proven real-world project experience designing, developing, and implementing AI-powered applications and solutions.

Key Responsibilities

• Design, develop, and implement AI-powered applications using LLMs.
• Build and maintain AI workflows and agent-based solutions using LangChain and LangGraph.
• Design and implement RAG architectures to enhance LLM responses using relevant enterprise data.
• Develop, integrate, and deploy AI solutions using Azure AI Foundry.
• Integrate LLMs with enterprise systems, APIs, vector databases, and external data sources.
• Optimize AI applications for performance, scalability, reliability, and response accuracy.
• Implement prompt engineering, context management, and retrieval optimization techniques.
• Troubleshoot, test, and improve AI models and application workflows.
• Collaborate with cross-functional teams to deliver production-ready AI solutions.

Mandatory Technical Skills

• LangChain: Strong hands-on experience developing LLM-powered applications.
• LangGraph: Experience building stateful, multi-step AI workflows and agentic applications.
• Large Language Models (LLMs): Experience with LLM integration, development, and implementation.
• Retrieval-Augmented Generation (RAG): Practical experience designing and implementing RAG pipelines.
• Azure AI Foundry: Hands-on experience building and deploying AI solutions using Azure AI Foundry.

Required Qualifications

• Strong understanding of LLM-based application architecture and generative AI solutions.
• Experience integrating AI components with APIs, data sources, and enterprise applications.
• Ability to develop, test, debug, and optimize AI-powered solutions.
• Strong analytical, problem-solving, and communication skills.