Agentic AI Operations Engineer

Rockwell Automation is a global technology leader focused on helping the world’s manufacturers be more productive, sustainable, and agile. With more than 28,000 employees who make the world better every day, we know we have something special. Behind our customers - amazing companies that help feed the world, provide life-saving medicine on a global scale, and focus on clean water and green mobility - our people are energized problem solvers that take pride in how the work we do changes the world for the better.

We welcome all makers, forward thinkers, and problem solvers who are looking for a place to do their best work. And if that’s you we would love to have you join us!

Job Description

As an Agentic AI Operations Engineer, you will support and operate the Generative AI and Agentic AI solutions that power our enterprise AI platform. Working under the guidance of senior architects and engineers, you will help deploy AI pipelines and agentic applications in production, ensuring they run reliably, securely. This is a hands-on operational role focused on keeping our AI systems healthy and improving.

You will report to the Engineering Manager.

Main Responsibilities

Agentic AI Application & Pipeline Operations:

• Deploy, configure, and maintain AI Agents that use Tools and Skills, including supporting MCP clients and servers within established frameworks.
• Operate and support Retrieval-Augmented Generation (RAG) pipelines. These pipelines include data ingestion, document processing, and promoting generation (e.g., Azure OpenAI or Gemini embeddings). Additionally, help maintain integrations with vector and NoSQL databases.
• Maintain the Azure Infrastructure that supports the AI Agents (Postgres, Redis, Grafana / Monitoring, Kubernetes Services, Application Gateway)
• Configure / Maintain a Service Mesh to support the AI Architecture

Monitor & Performance Support:

• Monitor model serving layers and data processing pipelines, identifying and escalating performance issues to maintain low latency and efficient resource use across the cloud environment.
• Implement and tune observability (logging, metrics, alerting) and respond to incidents to keep AI services available and reliable.
• Implement Grafana Dashboards for the existing infrastructure and usage

Security & Compliance Operations:

• Apply and uphold established security and data governance policies in daily operations, including PII filtering and guarded conversation frameworks.
• Support audits and compliance checks for AI products in production.

Infrastructure Automation & CI/CD:

• Use Terraform to provision and manage Azure infrastructure-as-code within existing standards.
• Maintain Continuous Integration/Continuous Deployment (CI/CD) pipelines to help automated, reproducible deployments.

The Essentials — You Will Have

• Bachelor's Degree.
• English proficiency for collaboration with global teams

The Preferred — You Might Also Have

• Typically requires +1 years of relevant work experience.
• Be able to work in diverse technical teams and adaptability to changes
• Proficient at Kubernetes Clusters Management
• Python experience
• Hands-on experience deploying, operating, or supporting Generative AI solutions, RAG pipelines, or multi-agent frameworks (any cloud vendor).
• +1 years of experience with a major cloud platform — Microsoft Azure (preferred), Amazon Web Services, or Google Cloud Platform (GCP).
• 1+ years of experience with MLOps and orchestration tooling such as Docker and Airflow.
• Exposure to vector search platforms like Azure Cosmos DB for PostgreSQL, Redis, Azure AI Search, or pgvector/Mongo Atlas.
• 1+ years of experience with observability/monitoring tooling and incident response.
• Familiarity with Scaled Agile Framework (SAFe) methodologies.

"This position is part of a job family. Experience will be the determining factor por position level and compensation"

What We Offer

Our benefits package includes …

• Comprehensive mindfulness programs with a premium membership to Calm.
• Volunteer Paid Time off available after 6 months of employment for eligible employees.
• Company volunteer and donation matching program – Your volunteer hours or personal cash donations to an eligible charity can be matched with a charitable donation.
• Employee Assistance Program.
• Personalized wellbeing programs through our OnTrack program
• On-demand digital course library for professional development... and other local benefits!

Rockwell Automation's hybrid policy expects employees to work at a Rockwell location at least on Mondays, Tuesdays, and Thursdays unless they have a business obligation out of the office.

We believe that employee diversity is an important element of our common future. We provide opportunities for talent growth with the entire organization. We support equality by celebrating the individuality of every person, regardless of their origin and identity. We appreciate the unique cultural pattern and variety of experiences in each of us. We invite all who want to join and change the world of Our organization.

#LI-Hybrid

#LI-JP1

Rockwell Automation’s hybrid policy aligns that employees are expected to work at a Rockwell location at least Mondays, Tuesdays, and Thursdays unless they have a business obligation out of the office.