ZipRecruiter

Log In

1

Freelance Retrieval Augmented Generation Jobs in Michigan

Judge Group, Inc.

Midlevel AI Developer

Ann Arbor, MI · On-site

$50 - $55/hr

Implement retrieval-augmented generation (RAG), semantic search, and knowledge retrieval solutions. Evaluate, benchmark, and optimize AI model performance, focusing on quality, cost, and latency.

Saanvi Technologies

Machine Learning Engineer 3

Dearborn, MI · On-site

$105K - $126K/yr

Develop and implement LLM-powered applications, including Retrieval-Augmented Generation (RAG), prompt orchestration, agentic workflows, and tool integrations. Create scalable APIs and AI services ...

General Motors

AI Agent Engineer

Warren, MI · On-site

$150 - $200/hr

AI/ML and platform integration + Leverage LLMs and related AI services (e.g., retrieval-augmented generation, embeddings, vector search) to power agent capabilities. + Integrate agents with ...

Orbotech

AI Software Engineer - Operations

Ann Arbor, MI · On-site

$90K - $153K/yr

Implement retrieval-augmented generation (RAG) architectures using internal and external data sources * Design data pipelines and connectors to enterprise systems (e.g., databases, APIs, knowledge ...

KLA

AI Software Engineer|Manufacturing

Ann Arbor, MI · On-site

$111K - $188K/yr

Implement retrieval-augmented generation (RAG) architectures using internal and external data sources * Design data pipelines and connectors to enterprise systems (e.g., databases, APIs, knowledge ...

General Motors

AI Agent Engineer

Warren, MI · On-site +1

Leverage LLMs and related AI services (e.g., retrieval-augmented generation, embeddings, vector search) to power agent capabilities. * Integrate agents with enterprise systems, APIs, and data sources ...

Kla

AI Software Engineer - Operations

Ann Arbor, MI · On-site

$90K - $153K/yr

Implement retrieval-augmented generation (RAG) architectures using internal and external data sources * Design data pipelines and connectors to enterprise systems (e.g., databases, APIs, knowledge ...

General Motors

AI Agent Engineer

Warren, MI · On-site

Leverage LLMs and related AI services (e.g., retrieval-augmented generation, embeddings, vector search) to power agent capabilities. * Integrate agents with enterprise systems, APIs, and data sources ...

next page

Showing results 1-20

All JobsRetrieval Augmented Generation JobsFreelance Retrieval Augmented Generation JobsFreelance Retrieval Augmented Generation Jobs in Michigan

Freelance Retrieval Augmented Generation information

What is a freelance retrieval augmented generation specialist?

A Freelance Retrieval Augmented Generation (RAG) specialist is an independent professional who designs, develops, and implements AI systems that combine retrieval-based methods with generative models. RAG specialists help organizations enhance their applications by integrating large language models (LLMs) with external data sources, allowing the AI to access and utilize up-to-date information beyond its training data. Their work involves tasks such as building pipelines for document indexing and retrieval, fine-tuning models, and optimizing the integration for accuracy and efficiency. Freelance RAG specialists typically work on a contract basis, offering flexibility and expertise for businesses that need advanced AI solutions.

What are the key skills and qualifications needed to thrive as a freelance retrieval augmented generation specialist?

To thrive as a Freelance Retrieval Augmented Generation (RAG) Specialist, you need expertise in natural language processing, information retrieval, and machine learning, typically supported by a degree in computer science or related fields. Proficiency with frameworks like Hugging Face Transformers, vector databases (e.g., FAISS, Pinecone), and cloud platforms is often required. Strong problem-solving, effective communication, and adaptability set standout professionals apart in this role. These skills ensure the development and fine-tuning of high-performance RAG systems that deliver accurate, contextually relevant results for clients.

How does a freelance retrieval augmented generation specialist typically collaborate with client teams during a project?

Freelance Retrieval Augmented Generation (RAG) specialists often work closely with client data scientists, engineers, and project managers to understand business requirements and integrate RAG systems into existing workflows. Communication is usually handled through regular virtual meetings, shared documentation, and sometimes real-time collaboration tools. Freelancers are expected to deliver modular, well-documented solutions and provide guidance on optimizing retrieval pipelines or fine-tuning models. This collaborative dynamic ensures that RAG implementations are aligned with client goals and technical standards, while also allowing freelancers to contribute innovative solutions based on their expertise.

What are popular job titles related to Freelance Retrieval Augmented Generation jobs in Michigan?

For Freelance Retrieval Augmented Generation jobs in Michigan, the most frequently searched job titles are:

What job categories do people searching Freelance Retrieval Augmented Generation jobs in Michigan look for?

The top searched job categories for Freelance Retrieval Augmented Generation jobs in Michigan are:

What cities in Michigan are hiring for Freelance Retrieval Augmented Generation jobs?

Cities in Michigan with the most Freelance Retrieval Augmented Generation job openings:

Freelance Retrieval Augmented Generation jobs near you

Senior Azure AI Foundry Engineer

Detroit, MI • On-site

Interon IT Solutions
See more jobs at Interon IT Solutionsexternal

$59.50 - $77.25/hr

Contractor

Re-posted 18 days ago

Job description

Job Title: Azure AI Foundry Engineer

Location: Lansing/Detroit, Michigan (Hybrid)

Client: Cognizant

Employment Type: W2

Experience: 8+ Years


Job Description:

We are seeking an experienced Azure AI Foundry Engineer to design, develop, and deploy enterprise-grade generative AI solutions on the Microsoft Azure platform. The ideal candidate should have strong experience with Azure AI Foundry, Azure OpenAI, Retrieval-Augmented Generation, AI agents, Python, and cloud-native application development.


Key Responsibilities

Design and develop generative AI applications using Azure AI Foundry and Azure OpenAI.
Build Retrieval-Augmented Generation solutions using Azure AI Search, vector databases, embeddings, and enterprise data sources.

Develop AI agents capable of interacting with APIs, databases, documents, and other business systems.

Design prompt workflows, system instructions, tool-calling processes, and multi-step agent workflows.

Develop backend AI services and APIs using Python, FastAPI, Flask, or similar frameworks.
Integrate structured and unstructured data from Azure Data Lake, Blob Storage, SQL databases, SharePoint, and enterprise applications.

Implement document ingestion, chunking, embedding, indexing, retrieval, and response-generation pipelines.

Evaluate AI applications for response accuracy, relevance, groundedness, safety, latency, and overall performance.

Implement responsible AI controls, content filtering, prompt-injection protection, access controls, and data-security standards.

Monitor AI applications using Azure Monitor, Application Insights, logging, tracing, and Foundry observability capabilities.

Deploy and manage AI solutions using Azure Functions, Azure App Service, Azure Container Apps, AKS, or similar Azure services.

Build automated CI/CD pipelines using Azure DevOps or GitHub Actions.

Collaborate with data engineers, data scientists, architects, business analysts, and product teams.

Troubleshoot issues related to model responses, data retrieval, integrations, application performance, and cloud deployment.

Prepare technical design documents, architecture diagrams, deployment guides, and operational documentation.


Required Skills

6+ years of overall software engineering, data engineering, cloud, or AI development experience.
Strong hands-on experience with Azure AI Foundry or Microsoft Foundry.

Experience with Azure OpenAI models, embeddings, chat completions, and model deployments.
Strong experience developing RAG-based applications.

Hands-on experience with Azure AI Search, vector search, semantic search, and hybrid search.
Strong programming experience with Python.

Experience developing REST APIs using FastAPI, Flask, or similar frameworks.

Experience with prompt engineering, function calling, tool calling, and AI agent development.
Understanding of LLM evaluation, hallucination reduction, groundedness, responsible AI, and content safety.

Experience with Azure services such as Blob Storage, Data Lake, Key Vault, Functions, App Service, Container Apps, AKS, and Application Insights.

Experience working with SQL, NoSQL, document databases, or vector databases.

Experience with Git, Azure DevOps, GitHub Actions, Docker, and CI/CD processes.