Mid-Level Generative AI Engineer

Digital HIE Inc; Atlanta (GA); Remote; USD 103,000 - 117,000; Full time

Job summary

Digital HIE Inc is seeking a mid-level Generative AI Engineer to design, develop, and support production-ready AI applications. The role is based in Atlanta, GA (remote) with Continental United States (Remote / U.S.-Based) coverage, focusing on Python backend services and GenAI solutions powered by Azure OpenAI with RAG and agentic AI workflows.

You will work across model integration, retrieval pipelines, agent orchestration, LLM evaluation, and operational monitoring to improve accuracy,

Qualifications

• Bachelor’s degree in a related field or equivalent experience.
• 3+ years of software development experience.
• At least 1+ year of hands-on Generative AI development experience.
• Strong Python backend development experience.
• Hands-on experience with FastAPI and asynchronous APIs.
• Experience with RAG-based knowledge assistants, chatbots, or AI apps.

Responsibilities

• Design and maintain production-grade Generative AI applications and web services.
• Build Python backend services and APIs using FastAPI and Pydantic.
• Develop RAG pipelines with embeddings, vector search, and citations.
• Integrate Azure OpenAI and related Azure services into solutions.
• Develop AI agents and multi-agent workflows with tool calling and structured outputs.
• Integrate AI apps with REST APIs, databases, and enterprise services.
• Evaluate LLMs to improve accuracy, retrieval quality, and cost efficiency.
• Implement logging, monitoring, tracing, and metrics for observability.
• Collaborate in code reviews, automated tests, CI/CD, and Agile processes.

Skills

Python

FastAPI

RAG

Azure OpenAI

LLM evaluation

Agile

CI/CD

DevSecOps

Asynchronous APIs

Agent workflows

Education

Bachelor’s degree

Tools

Azure OpenAI

Azure AI Foundry

Azure AI Search

Job description

Digital HIE Inc is seeking a mid-level Generative AI Engineer to help design, develop, and support production-ready generative AI applications. The role is based in Atlanta, GA (remote) with Continental United States (Remote / U.S.-Based) coverage, and focuses on building Python backend services and GenAI solutions powered by Azure OpenAI with RAG and agentic AI workflows.

You will work across the stack of model integration and application reliability, including retrieval pipelines, agent orchestration, LLM evaluation, and operational monitoring to improve accuracy, retrieval quality, grounding, performance, and cost efficiency.

Key Responsibilities

• Design, develop, and maintain production-grade Generative AI applications and web-based AI solutions.
• Build Python backend services and APIs using FastAPI, Pydantic, and asynchronous programming.
• Develop RAG pipelines, including document processing, chunking, embeddings, vector search, hybrid search, and source citations.
• Integrate Azure OpenAI along with Azure AI Foundry, Azure AI Search, databases, and enterprise services.
• Develop AI agents and multi-agent workflows using tool/function calling, structured outputs, and conversation context management.
• Integrate AI applications with REST APIs, enterprise data sources, databases, and MCP-based tools.
• Conduct LLM evaluation to improve response accuracy, retrieval relevance, grounding, performance, latency, and cost efficiency.
• Implement logging, monitoring, tracing, and metrics for troubleshooting and AI application performance visibility.
• Troubleshoot production issues, resolve defects, and support AI application deployments.
• Participate in code reviews, automated testing, CI/CD, and Agile development activities.
• Collaborate with cross-functional engineering and DevSecOps teams.

Requirements

• Bachelor’s degree in Computer Science, Information Technology, Engineering, or a related field.
• Minimum 3+ years of software development experience.
• At least 1+ year of hands-on Generative AI development experience.
• Strong Python and backend development experience.
• Hands-on experience with FastAPI, Pydantic, asynchronous APIs, or equivalent frameworks.
• Experience building and deploying RAG-based knowledge assistants, chatbots, or AI applications.
• Practical experience with Azure OpenAI, Azure AI Search, and Azure cloud services.
• Hands-on experience with document processing, text chunking, embeddings, vector databases, hybrid search, and citations.
• Hands-on experience developing agentic AI workflows using tool/function calling and structured outputs.
• Experience with LangGraph, PydanticAI, Microsoft Agent Framework, Azure AI Foundry Agent Service, or similar frameworks.
• Experience integrating APIs, databases, and external enterprise services.
• Knowledge of Git, code reviews, automated testing, CI/CD, and Agile methodologies.
• Ability to evaluate and troubleshoot LLM applications using test datasets, logs, and traces.
• Must be a U.S. Citizen or Lawful Permanent Resident (Green Card Holder).
• Must be able to obtain and maintain the required Public Trust or suitability determination.

Preferred Qualifications

• Experience with AI observability tools such as Langfuse, Pydantic Logfire, OpenTelemetry, or similar.
• Experience with advanced RAG architectures and multi-agent systems.
• Experience with Model Context Protocol (MCP) integrations.
• Knowledge of Docker and Azure application deployment services.
• Frontend development experience with React, Angular, or TypeScript.
• Experience with open-source LLM hosting frameworks such as vLLM or SGLang.
• Knowledge of LLM fine-tuning and optimization, including PEFT, LoRA, QLoRA, and quantization.
• Experience with AWS Bedrock and Amazon OpenSearch Service.

Technologies

• Python, Azure OpenAI, Azure AI Search, Azure AI Foundry, FastAPI, Pydantic, RAG
• Vector search, hybrid search, REST APIs
• LLM evaluation
• LangGraph, PydanticAI, Microsoft Agent Framework, Azure AI Foundry Agent Service, MCP
• Git

Additional Details

• Salary: USD $75 - $85 per hour
• Employment Type: Full-Time / Contract (as applicable)
• Number of Positions: 2
• Work Location: In person

Work Authorization: U.S. Citizens and Green Card Holders Only.

Experience alignment (preferred): RAG Development (3 years), Azure AI (3 years), Agentic AI Development (3 years).