Cloud /AI Architect with RAG and Agentic AI with AWS Exp

Infinity Tech Group; Stamford (CT); On-site; USD 150,000 - 190,000; Full time

Job summary

Infinity Tech Group in Stamford, CT is seeking an experienced Cloud/AI Architect to design enterprise-grade Agentic AI systems and define scalable, secure architecture standards.

You will architect AI pipelines across AWS Agent Core, Google Vertex AI, LangChain/LangGraph, and vector stores, delivering governance, reliability, and cost-efficient solutions for autonomous agents and RAG use cases across enterprise teams.

Qualifications

• Designing and implementing scalable cloud/AI architectures for enterprise AI
• Experience with agentic/ autonomous AI systems and governance
• Experience with RAG pipelines, knowledge retrieval, and vector databases
• Strong leadership, collaboration, and communication across technical teams

Responsibilities

• Architect and implement Agentic AI pipelines with multi-step reasoning and orchestration
• Build enterprise-grade RAG systems including embeddings, vector stores, and retrieval optimization
• Define cloud architecture patterns for AI workloads (compute, storage, security, cost)
• Evaluate LLM providers and AI frameworks for enterprise use cases
• Work with LangChain/LangGraph, CrewAI, Bedrock Agents, Vertex AI ecosystems
• Collaborate with Data/Security/Cloud/Platform teams to meet scalability and compliance
• Develop reusable architecture blueprints and reference implementations
• Provide technical leadership and mentorship to engineering teams
• Evaluate new cloud AI services and adoption opportunities
• Translate business requirements into scalable, secure AI architectures

Skills

Cloud architecture

Technical leadership

Stakeholder management

Communication

Education

Bachelor's degree in CS/Engineering

Tools

AWS

Google Cloud Platform

Vertex AI

LangChain

LangGraph

CrewAI

Bedrock Agents

OpenSearch

Pinecone

pgvector

Job description

HIRING NOW | CLOUD / AI ARCHITECT AGENTIC AI

We are looking for an experienced Cloud/AI Architect to design and build enterprise-grade Agentic AI systems and define the architecture standards for scalable, secure, and production-ready AI solutions.

Location: Stamford, CT

Duration: 12 Months

Engagement: 1099 or W2

Visa: / GC

Role: Cloud/AI Architect Agentic AI

About The Role

This role will focus on architecting scalable AI solutions using AWS Agent Core, Google Cloud Platform Vertex AI, and other cloud-native AI services. You will help define the technical strategy for how enterprise teams build, deploy, govern, and scale autonomous AI agents and knowledge retrieval systems.

Key Responsibilities

• Architect and implement Agentic AI pipelines involving multi-step reasoning, tool usage, orchestration, and autonomous workflows.
• Build enterprise-grade RAG (Retrieval-Augmented Generation) systems, including data ingestion, chunking strategies, embedding pipelines, vector stores, and retrieval optimization.
• Define cloud architecture patterns for AI workloads covering compute, storage, networking, security, scalability, and cost optimization.
• Evaluate and select LLM providers, AI orchestration frameworks, and vector databases based on enterprise requirements.
• Work with technologies/frameworks such as AWS Agent Core, Google Cloud Platform Vertex AI, LangChain, LangGraph, CrewAI, Bedrock Agents, and equivalent platforms.
• Work with vector databases and search technologies such as OpenSearch, Pinecone, pgvector, or equivalent solutions.
• Collaborate with Data Engineering, Security, Cloud, Platform, and Engineering teams to ensure enterprise AI solutions meet scalability, reliability, security, and compliance standards.
• Develop reusable architecture blueprints, reference architectures, and implementations for Agentic AI and RAG use cases.
• Provide technical leadership and mentorship to engineering teams implementing AI solutions.
• Evaluate emerging cloud AI services and recommend adoption where they provide measurable business value.
• Translate business requirements into scalable, secure, and production-ready AI architectures.

What We're Looking For

• Experience designing and implementing Agentic AI / Autonomous AI systems
• Strong experience with AWS and/or Google Cloud Platform cloud architecture
• Hands-on experience with RAG architecture and enterprise knowledge retrieval
• Experience with LLMs, prompt engineering, embeddings, vector databases, and AI orchestration
• Experience with LangChain / LangGraph / CrewAI / Bedrock Agents / Vertex AI or equivalent frameworks
• Experience designing enterprise AI infrastructure covering security, networking, compute, storage, scalability, and cost optimization
• Experience establishing Agentic AI governance frameworks, including guardrails, audit trails, autonomy limits, and responsible AI controls
• Exposure to multiple LLM providers and the ability to determine which model/provider is appropriate for different use cases
• Experience building reusable AI platforms, infrastructure patterns, or architecture frameworks adopted across multiple teams
• Strong stakeholder management, communication, architecture, and technical leadership skills

WHY THIS ROLE?

This is more than a traditional architecture position.

You Will Have The Opportunity To

• Influence how AI is built and deployed across the enterprise
• Establish reusable standards and architecture patterns for Agentic AI
• Solve complex, open-ended AI architecture challenges
• Help define enterprise approaches to RAG, AI agents, governance, and LLM adoption
• Work toward becoming a key technical leader for Agentic AI architecture