AI Architect

Siri InfoSolutions Inc; Arden Hills (MN); On-site; USD 140,000 - 190,000; Part time

Job summary

Siri InfoSolutions Inc. seeks an AI Architect to lead the design and deployment of Agentic AI solutions on AWS cloud-native services, including Bedrock and SageMaker. The role targets 8–10 years of IT experience with 6+ years in AI/ML, and 2+ years in GenAI/LLM technologies.

You will build autonomous agents, RAG pipelines, and knowledge assistants for enterprise-scale applications. The position is on-site in Arden Hills, MN, for a 6+ month contract, offering opportunities to design scalable AI

Qualifications

• Design, develop and deploy AI/GenAI solutions across enterprise applications.
• Support architects and delivery teams in implementing AI use cases across the enterprise.
• 8-10 yrs overall IT experience.
• 6+ yrs in AI/ML with about 2+ yrs in Gen AI and LLM based solutions.

Responsibilities

• Design and implement Agentic AI solutions using AWS cloud-native services.
• Build autonomous AI agents capable of planning, reasoning, memory management & tool execution.
• Integrate AI agents with enterprise systems through APIs, database, event-driven architectures and microservices.
• Develop RAG pipelines and knowledge assistants.
• Implement prompt engineering and evaluation frameworks.
• Fine-tune or optimize AI model performance, latency, scalability & costs; implement monitoring, logging, evaluation, guardrails and observability for AI solutions.
• Support AI testing, validation and deployment.

Skills

Python

Rest APIs

Langchain

LangGraph

CrewAI

Amazon Bedrock

Sagemaker

AWS Lambda

Step Functions

EventBridge

CloudWatch

Vector databases

Prompt Engineering

ML fundamentals

Data preprocessing

Agentic AI implementation

Knowledge graph integration

Tools

Python

Rest APIs

Job description

Section

Details

Job Title

AI Architect

Job Type

Contract

Client Location

Arden Hills, MN

Work Arrangement

On site

Duration

6+ Months

Job Summary

AI Architect with 8 10 years of IT experience and strong expertise in AI/ML, Generative AI, LLMs, and Agentic AI solution architecture. Design and deploy scalable AI agents, RAG pipelines, and knowledge assistants using AWS services, Amazon Bedrock, SageMaker, LangChain/LangGraph, APIs, vector databases, and microservices. Drive enterprise AI implementation with expertise in prompt engineering, model optimization, observability, guardrails, testing, validation, and production deployment.

Key Responsibilities

• Design and implement Agentic AI solutions using AWS cloud-native services
• Build autonomous AI agents capable of planning, reasoning, memory management & tool execution
• Integrate AI agents with enterprise systems through APIs, database, event-driven achitectures and microservices
• Develop RAG pipelines and knowledge assistants
• Implement prompt engineering and evaluation frameworks
• Fine-tune or optimize AI model performance, latency, scalability & costs Implement monitoring, logging, evaluation, guardrails and observibility for AI solutions
• Support AI testing , validation and deployment.

Required Qualifications

• Design develop and deploy AI/GenAI solutions,
• Supporting architects and delivery teams in implementing AI use cases across the enterprise applications Experience-
• 8-10 yrs overall IT experience
• 6+ yrs in AI/ML with about 2+ yrs in Gen AI and LLM Based solutions

Skills Required:

• Python, Rest APIs
• Langchain / LangGraph /CrewAI
• Amazon Bedrock, Sagemaker
• AWS Lambda, Step functions, Eventbridge, Cloudwatch
• Vector databases
• Prompt Engineering
• Rest APIs
• ML fundamentals/ techniques
• Data preprocessing
• Agentic AI implementation
• Knowledge graph integration