AI Architect

This is a remote position.

We are seeking an experienced AI Architect to design, develop, and deliver scalable enterprise Artificial Intelligence solutions. The role focuses on Generative AI, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI, and cloud-based AI architectures.

The ideal candidate will bring strong hands-on Python development experience, enterprise architecture expertise, and the ability to lead AI solutions from design through production deployment. This is a 12-month W2 contract opportunity based in the Boston area or New Jersey or Franklin, with a hybrid arrangement requiring approximately 3–4 days onsite per week.

Requirements

• 8–10+ years of relevant software engineering, AI engineering, or enterprise architecture experience preferred.
  

• Strong hands-on Python programming and backend application development.
  

• Proven experience designing and implementing enterprise Generative AI and Large Language Model (LLM) solutions.
  

• Hands-on experience with Agentic AI, autonomous AI agents, multi-agent systems, and agent orchestration.
  

• Practical experience with LangChain and LangGraph for LLM workflows and agent-based applications.
  

• Strong experience implementing Retrieval-Augmented Generation (RAG) solutions.
  

• Experience with vector databases, embeddings, semantic search, and document retrieval architectures.
  

• Experience designing and integrating LLM applications through REST APIs, FastAPI, or similar frameworks.
  

• Strong understanding of enterprise AI architecture, distributed systems, microservices, and cloud-native applications.
  

• Experience deploying AI applications on AWS, Microsoft Azure, or Google Cloud Platform.
  

• Experience designing secure, scalable, reliable, and production-ready AI systems.
  

• Understanding of AI model evaluation, LLMOps, monitoring, observability, security, and governance.
  

• Experience collaborating with engineering teams, business stakeholders, and technical leadership.
  

• Strong problem-solving, architecture design, and technical communication capabilities.
  
  

Preferred Experience

• AWS Bedrock, Azure OpenAI, Azure AI services, or equivalent enterprise AI platforms.
  

• Docker, Kubernetes, CI/CD pipelines, and cloud infrastructure automation.
  

• Multi-agent orchestration, tool calling, Model Context Protocol (MCP), and advanced Agentic AI frameworks.
  

• Enterprise AI guardrails, prompt engineering, model evaluation, and cost optimization.
  

• Experience leading end-to-end AI implementations from architecture through production delivery.
  
  

Employment and Work Arrangement Requirements

• Location: Boston, Massachusetts, or New Jersey or Franklin.
  

• Hybrid work arrangement requiring approximately 3 - 4 days onsite per week.
  

• One-year W2 contract engagement.
  

• Candidates must have appropriate U.S. work authorization for W2 employment.
  

• Willingness to work onsite at the assigned location and collaborate with distributed engineering teams.