Agentic AI Engineer - Production-Ready LLMs & RAG

Kelly Services; Phoenix (AZ); On-site; USD 165,000 - 185,000; Full time

Job summary

Kelly Services is recruiting an experienced AI Engineer for large-scale agentic AI and Generative AI initiatives in the Phoenix area. You will design, build and deploy production-grade AI applications, and help scale internal platforms and customer-facing products.

You will work on multi-agent orchestration, RAG architectures, LLM integration, and cloud-native solutions on AWS and/or GCP, with a strong emphasis on real-world impact and production readiness.

Qualifications

• Strong software engineering experience with Python.
• Hands-on experience building Agentic AI solutions.
• Experience working with Large Language Models (LLMs).
• Knowledge of agent orchestration frameworks and multi-agent systems.
• Experience designing and implementing RAG architectures.
• Proven ability to develop and deploy production AI applications.
• Backend development and API design experience.
• Cloud experience with AWS and/or GCP.
• Ability to clearly articulate personal contributions, technical decisions, and system architecture.

Responsibilities

• Design, build, and deploy production-grade Agentic AI applications.
• Develop multi-agent workflows and orchestration frameworks.
• Build and optimize RAG (Retrieval-Augmented Generation) solutions.
• Integrate LLMs into enterprise-scale platforms and products.
• Develop scalable APIs and backend services using Python.
• Architect cloud-native AI solutions in AWS and/or GCP.
• Collaborate with engineering, product, and business teams to deliver impactful AI capabilities.
• Contribute to AI architecture, governance, evaluation, and monitoring best practices.
• Drive AI initiatives from concept through production deployment.

Skills

Python

LLMs

Agentic AI

API design

Cloud (AWS/GCP)

Backend development

Orchestration/multi-agent

Tools

Kubernetes

Kafka

React

TypeScript

Job description

Kelly Services is recruiting an experienced AI Engineer for large-scale agentic AI and Generative AI initiatives in the Phoenix area. You will design, build and deploy production-grade AI applications, and help scale internal platforms and customer-facing products.

You will work on multi-agent orchestration, RAG architectures, LLM integration, and cloud-native solutions on AWS and/or GCP, with a strong emphasis on real-world impact and production readiness.