Senior Generative AI Agent Architect for Enterprise

DeWinter Group; Boston (MA); Hybrid; USD 140,000 - 190,000; Full time

Job summary

DeWinter Group in the Boston area is seeking a Senior Generative AI Engineer / AI Agent Developer to design, develop, and deploy cutting-edge AI agents and agentic workflows for enterprise challenges. You will work with cross-functional teams to deliver scalable, production-grade AI solutions that align with business goals.

You will deploy LLM-based systems, RAG, and orchestration frameworks, ensuring security, performance, and maintainability.

Qualifications

• Hands-on experience with enterprise AI platform development and governance.
• Proven ability to design, build, test, and deploy AI agents.
• Strong knowledge of LLMs, prompting, and AI workflow orchestration.
• Solid software engineering fundamentals and API integration.

Responsibilities

• Architect, develop, and deploy AI agents and agentic workflows.
• Leverage LLMs, RAG, and orchestration frameworks for enterprise needs.
• Collaborate with cross-functional teams to identify AI use cases.
• Ensure security, performance, scalability, and maintainability of AI solutions.
• Help establish enterprise AI standards and governance.
• Partner with stakeholders to enable AI deployment across the org.

Skills

Azure AI Foundry

Azure AI services

AI agents dev

LLMs & prompt engineering

Python

AI workflow orchestration

Tool calling

Agent architectures

API integration

Greenfield environments

Education

Bachelor’s degree in Computer Science/Engineering or related field

Tools

LangGraph

LangChain

LangSmith

AWS Bedrock

Google Cloud AI

Claude

GitHub Copilot

Cursor

Windsurf

Slingshot

Job description

DeWinter Group in the Boston area is seeking a Senior Generative AI Engineer / AI Agent Developer to design, develop, and deploy cutting-edge AI agents and agentic workflows for enterprise challenges. You will work with cross-functional teams to deliver scalable, production-grade AI solutions that align with business goals.

You will deploy LLM-based systems, RAG, and orchestration frameworks, ensuring security, performance, and maintainability.