Senior Site Reliability Engineer (AI)

TL;DR

Senior Site Reliability Engineer (AI/DevOps): Building AI-powered agentic workflows to automate SRE operations and reduce operational toil with an accent on LLM integration, infrastructure provisioning, and incident diagnostics. Focus on designing intelligent automation systems, building internal developer tools, and measuring toil reduction through data-driven approaches.

Location: Hybrid in Dublin, Ireland

Company

hirify.global is an Exposure Management company helping thousands of organizations worldwide understand and reduce cyber risk.

What you will do

• Design and build AI-powered agentic workflows for incident investigation, infrastructure provisioning, and deployment reliability.
• Develop internal developer tools, including CLI tools and IDE plugins, for use across the engineering organization.
• Integrate AI pipelines across the SRE tech stack, including Kubernetes, Terraform, Helm, and AWS APIs.
• Optimize the accuracy and reliability of agent pipelines using prompt engineering, RAG, and evaluation frameworks.
• Participate in the SRE on-call rotation to identify real-world toil and convert it into automation opportunities.
• Collaborate with distributed teams to identify automation gaps and deliver tools that increase engineering efficiency.

Requirements

• 5+ years of experience in SRE, platform engineering, or infrastructure engineering.
• Strong software engineering skills with proficiency in Python for production-quality code.
• Experience integrating LLMs and AI into production infrastructure contexts.
• Deep experience with Kubernetes (EKS preferred), Terraform, and CI/CD pipeline development.
• Strong knowledge of AWS services and observability platforms like Datadog or Coralogix.
• Solid background in Linux systems and bash scripting.

Nice to have

• Hands-on experience building multi-step agent pipelines and RAG architectures.
• Experience with Claude, OpenAI APIs, AWS Bedrock, or SageMaker.
• Proficiency in Go, Java, or Kotlin.
• Experience building evaluation and testing frameworks for AI/ML systems.
• Familiarity with distributed systems patterns, including event-driven architectures.

Culture & Benefits

• Collaborative environment with a culture of belonging, respect, and excellence.
• Opportunity to work with highly talented peers in the cybersecurity industry.
• Emphasis on asynchronous collaboration and documented decision-making.
• Commitment to Equal Employment Opportunity (EEO) across all levels.