AI Engineer (Python/LangGraph/Agentic AI)

Summary:
Develop and roll out new observability and automation solutions, driving increased demand for development capacity for Site Reliability Engineering (AIOps and Agentic AI).

Key Responsibilities:

AIOps & Agentic AI Engineering

• Develop Python and/or LangGraph scripts and agentic AI workflows to automateoperational tasks, diagnostics, and remediation.
• Build and integrate AIOps capabilities for predictive alerting, anomaly detection,and intelligent event correlation across infrastructure and applications
• Design and operationalise agentic AI solutions that augment incident response and reduce manual intervention.
• Develop self-healing and auto-remediation workflows driven by AI/ML and event correlation insights.

Infrastructure Automationand CI/CD

• Develop infrastructure automation to provision, configure, and manage systems in aconsistent, auditable manner.
• Manage automation and AI code through GitHub, applying version control, code review,and collaboration best practices.
• IntegrateAIOps and automation components into CI/CD pipelines for continuous testing,validation, and deployment.

Observability, Reliability& Collaboration

• Implement observability and event correlation across metrics, logs, and traces to enable proactive reliability management.
• Champion SRE frameworks and reliability practices, embedding AIOps into the delivery life cycle
• Collaborate with Application, Infrastructure, Cloud, and Cyber teams to enable predictive incident prevention and root-cause transparency
• Maintain documentation and runbooks, and mentor engineers on AIOps and automation best practices.