AI-Driven Cloud Infra Engineer for Agentic Ops

IBM; Calgary; On-site; CAD 120,000 - 180,000; Full time

Job summary

IBM Canada is seeking engineers to join our Cloud Reliability team, building an AI-powered operations system that enables scalable incident investigation and troubleshooting. You will integrate large language models into production-grade tools and collaborate with cross-functional teams to deliver secure, reliable AI-driven workflows.

The role emphasizes distributed systems, Kubernetes, security, and a product-minded approach to ambiguous problems, with a fast-paced environment and opportunities

Qualifications

• Strong software engineering fundamentals and production-systems experience.
• Proficiency in Python.
• Experience integrating large language models into real applications.
• A practical, product-minded approach to ambiguous problems and the ability to iterate quickly.
• A self-starter with strong problem-solving skills and the ability to work in a fast-paced environment.

Responsibilities

• Design, build, and operate an AI-powered operations system that engineers across Confluent rely on for investigation and troubleshooting.
• Build the tools and integrations that let AI systems securely query operational data and act on production infrastructure.
• Develop agentic workflows and reasoning loops, and improve their accuracy, latency, and reliability over time.
• Build evaluation frameworks and feedback loops to measure and continuously improve the quality of AI-generated investigations.
• Strengthen the security and access model around AI-driven operations, including least-privilege access and comprehensive auditing.
• Partner with cross-functional engineering teams to turn operational expertise into automated, AI-assisted workflows.

Skills

Software engineering

Python

LLM integration

Product-minded

Fast-paced environment

Education

Master's Degree

Tools

Kubernetes

Job description

IBM Canada is seeking engineers to join our Cloud Reliability team, building an AI-powered operations system that enables scalable incident investigation and troubleshooting. You will integrate large language models into production-grade tools and collaborate with cross-functional teams to deliver secure, reliable AI-driven workflows.

The role emphasizes distributed systems, Kubernetes, security, and a product-minded approach to ambiguous problems, with a fast-paced environment and opportunities