Agentic AI Operations Engineer

2 hours ago

Medellín, ColombiaMid Level

Responsibilities

Deploy, configure, maintain, and support agentic AI applications, AI agents, Tools and Skills, and MCP clients and servers.
Operate RAG pipelines covering data ingestion, document processing, embeddings, and integrations with vector and NoSQL databases.
Maintain Azure infrastructure supporting AI agents, including Postgres, Redis, Grafana, monitoring, Kubernetes services, and Application Gateway.
Configure and maintain a service mesh supporting the AI architecture.
Monitor model-serving layers and data-processing pipelines, identify performance issues, and support low-latency, efficient cloud operations.
Implement observability through logging, metrics, alerting, and Grafana dashboards, and respond to incidents to maintain service availability and reliability.
Apply security and data-governance policies, including PII filtering and guarded conversation frameworks, and support audits and compliance checks.
Use Terraform to provision and manage Azure infrastructure as code and maintain CI/CD pipelines for automated deployments.

Bachelor’s degree.
English proficiency for collaboration with global teams.
Typically 3+ years of relevant work experience.
Ability to work in diverse technical teams and adapt to change.
Proficiency managing Kubernetes clusters.
Python experience.
Hands-on experience deploying, operating, or supporting Generative AI solutions, RAG pipelines, or multi-agent frameworks.
At least 2 years of experience with a major cloud platform, preferably Microsoft Azure, AWS, or Google Cloud Platform.
Experience with MLOps and orchestration tooling such as Docker and Airflow.
Exposure to vector search platforms such as Azure Cosmos DB for PostgreSQL, Redis, Azure AI Search, pgvector, or Mongo Atlas.
Experience with observability or monitoring tools and incident response.
Familiarity with Scaled Agile Framework methodologies.

Comprehensive mindfulness programs with a premium Calm membership.
Volunteer paid time off available after six months of employment for eligible employees.
Employee volunteer and donation matching program.
Employee Assistance Program.
Personalized wellbeing programs through the OnTrack program.
On-demand digital course library for professional development.
Hybrid work policy requiring employees to work at a Rockwell location at least Mondays, Tuesdays, and Thursdays unless they have a business obligation outside the office.

10,000+ employees