AI Architect (Full Stack – Generative AI)

Location: Charlotte, NC, USA (3 days onsite)

12 Months Contract 

Role Overview

We are looking for a hands-on AI Architect to design and build end-to-end Generative AI solutions. The role involves developing agentic workflows using LangChain/LangGraph, building RAG pipelines, and deploying scalable AI services on Google Vertex AI.

You will collaborate with product, data, and platform teams to deliver secure, scalable, and production-ready AI applications.

Key Responsibilities:

• Architect and develop agentic AI workflows using LangChain and LangGraph.
• Design and implement RAG pipelines including embeddings, document ingestion, and vector search.
• Work with vector databases such as Pinecone, Weaviate, Milvus, or FAISS.
• Deploy AI solutions using Google Vertex AI, Docker, and Kubernetes.
• Build full-stack AI applications using Python (FastAPI) / Node.js and React / Next.js.
• Implement evaluation, security, and governance frameworks for AI systems.
• Provide technical leadership and architecture guidance for AI platforms.

Required Qualifications

• 8–12 years of software engineering experience.
• 4 years building ML / Generative AI systems in production.
• Strong experience with LangChain, LangGraph, and RAG architectures.
• Hands-on experience with vector databases and LLM integrations.
• Experience with Google Vertex AI or other cloud platforms.
• Strong skills in Python, Docker, Kubernetes, and CI/CD.