Java Full Stack AI Engineer
Major IT services company · Miami, FL
- Location
- Miami, FL · 5 days/week onsite
- Salary band
- $60 – $60/hr
- Type
- Contract
- Level
- Senior
- Work authorization
- No sponsorship — now or in future
Stack
Java · React · TypeScript · Next.js · Node.js · Python · REST APIs · SSE · WebSockets · LLM APIs · RAG pipelines · AI agents · multi-tenant architecture · CI/CD · cloud-native infrastructure · ADF · row-level security · vector search · embeddings · containerization
About the role
Java Full Stack AI Engineer Miami, FL (ONSITE From Day 1) 06+ Months Contract Pay Rate - $60/hr on w2 Must Have Qualifications: Over all min 10+ years exp. 7+ years of professional experience with React and TypeScript. 7+ years of experience designing REST APIs and asynchronous backend systems. 5+ years of experience building applications using React and Next.js. 3+ years of experience integrating LLM APIs into production applications. 3+ years of experience implementing streaming UI patterns using SSE or WebSocket's. Strong experience building scalable multi-tenant applications. Hands-on experience with Node.js and Python backend development. Experience with AI orchestration workflows and conversation state management. Core Technology Stack Area Technologies/Capabilities: Frontend: React, Next.js, TypeScript, responsive UI, accessibility, performance optimization Backend: Node.js, Python, RESTful APIs, asynchronous services Real-Time: SSE, WebSocket's, token-level streaming AI / LLM: LLM APIs, tool calling, structured JSON outputs, orchestration, conversation state AI Architecture: RAG pipelines, AI agents, multi-step workflows. Architecture: Scalable multi-tenant applications, row-level security DevOps/Cloud : CI/CD, deployment automation, cloud-native infrastructure Summary: We are seeking an experienced Full-Stack AI Engineer to design, build, and scale production-grade AI applications. The ideal candidate combines strong frontend expertise in React, Next.js, and TypeScript with backend development in Node.js and Python, and has hands-on experience integrating LLM APIs, real-time streaming interfaces, RAG pipelines, AI agent workflows, and scalable multi-tenant architectures. Day-to-Day Responsibilities: Design and develop scalable full-stack AI applications using React, Next.js, TypeScript, Node.js, and Python. Own the full UI lifecycle from wireframe through production, including accessibility, responsiveness, and performance optimization. Develop streaming conversational interfaces using Server-Sent Events (SSE) and WebSocket's. Implement token-level streaming for real-time AI response rendering. Build and maintain RESTful APIs and asynchronous backend services. Integrate and orchestrate LLM APIs, tool calling, and multi-step AI workflows. Collaborate with AI/ML engineers to integrate structured JSON outputs into frontend rendering pipelines. Design scalable multi-tenant architectures with row-level security. Build and optimize Retrieval-Augmented Generation (RAG) pipelines and AI agent workflows. Support deployment automation, CI/CD, and cloud-native infrastructure operations. Collaborate effectively with globally distributed engineering and product teams. Preferred Technical Expertise: Experience with RAG architectures, vector search, embeddings, and AI agent frameworks. Overall understanding of ADF & JAVA frameworks Understanding of LLM tool/function calling, structured outputs, prompt orchestration, and stateful conversational applications. Experience with cloud-native deployment patterns, containerization, observability, and CI/CD. Strong understanding of frontend performance, accessibility standards, secure API design, and production engineering best practices.
Recruiter contact
Unlock this recruiter's name, email and phone for a one-time $100. Payment is per role — you only pay for the introductions you actually want.
Want the full job-search package instead? Talk to us →
The recruiter's details are not public. Helen makes the introduction, checks your resume against the requirements first, and follows up on the reply.