AI-ML / RAG Architect

Job Title: AI-ML / RAG Architect

Location : Plano, TX (Remote work accepted, however we will prefer local candidates who can go onsite once in a while)-Local

Duration : 12+ Months Contract Role

Teams Meeting Interview

Job Description:

We are looking for a hands-on AI-ML / RAG Architect with 15+ years of experience to design and deliver enterprise Generative AI applications across AI, frontend, backend, data, and cloud platforms.

Key Responsibilities

• Architect enterprise Generative AI, RAG, conversational AI, and agentic AI solutions using Azure OpenAI and OpenAI APIs.
• Design agentic workflows using LangChain, LangGraph, Deep Agents, CrewAI, and MCP.
• Build MCP-based tools, multi-agent workflows, tool calling, orchestration, and human-in-the-loop solutions.
• Design enterprise Text-to-SQL / Natural-Language-to-SQL solutions that translate business questions into secure database queries.
• Implement schema-aware SQL generation, query validation, read-only SQL enforcement, RBAC-based data filtering, and safe query execution.
• Ground AI responses using SQL results, enterprise documents, RAG evidence, citations, and structured outputs.
• Design RAG solutions with vector/search retrieval, metadata filtering, prompt engineering, response validation, and hallucination controls.
• Design React frontend architecture for AI chat, conversational analytics, dashboards, admin screens, and enterprise workflows.
• Implement real-time AI experiences using SSE streaming, REST APIs, conversation history, citations, feedback, and error handling.
• Design frontend workflows for file uploads, attachments, document-processing status, AI-generated results, and data visualizations.
• Build scalable backend services using FastAPI, asynchronous processing, Pydantic, SQLAlchemy, and PostgreSQL.
• Build document-processing pipelines for Excel, PDF, Word, and PowerPoint.
• Architect AWS solutions using ECS/Fargate, S3, RDS, DynamoDB, CloudFront, WAF, IAM, EventBridge, and CloudWatch.
• Integrate Azure OpenAI, Microsoft Entra ID, Microsoft Graph, and SharePoint.
• Implement enterprise security using OAuth 2.0, JWT, RBAC, IAM, secrets management, prompt-injection protection, and least-privilege access.
• Establish LangSmith tracing, LLM evaluations, prompt regression, token/cost monitoring, latency monitoring, hallucination testing, and AI safety testing.
• Define infrastructure and deployment using Terraform, Docker, and CI/CD.
• Lead architecture and code reviews across AI, React frontend, backend, databases, AWS, and Azure.

Required Skills

• 15+ years of software engineering and solution architecture experience.
• Strong hands-on Generative AI, Azure OpenAI, RAG, and Text-to-SQL experience.
• Deep Agents and MCP experience is mandatory.
• Strong experience with LangChain, LangGraph, agentic AI, and tool calling.
• Strong hands-on React and JavaScript/TypeScript experienceStrong backend API, PostgreSQL, and microservices experience.
• Strong AWS and Azure architecture experience.
• Experience with Terraform, Docker, CI/CD, OAuth/JWT, RBAC, and enterprise AI security.