Platform/SRE Engineer

Role Title: Platform/SRE Engineer
Location: Sheffield (3 days a week onsite is mandatory)
Duration: 30/11/2026
Rate: 525p/d via Umbrella 

Role Description:

Own deployment, observability, reliability, cost control, and production operations for the AI helpdesk platform.

Key responsibilities

• Build and manage CI/CD pipelines, infrastructure, and runtime environments for AI services.
• Deploy and operate model-serving, orchestration, and application workloads.
• Implement monitoring, tracing, alerting, logging, and operational dashboards.
• Manage scaling, release processes, rollback mechanisms, and production support.
• Optimize inference cost, latency, uptime, and system reliability.
• Create runbooks, incident response processes, and operational standards.

Required skills

• Strong experience in DevOps, SRE.
• Experience with Docker, Kubernetes, cloud platforms, and infrastructure as code.
• Experience with monitoring and observability tools.
• Familiarity with CI/CD, release automation, secrets management, and production support.
• Understanding of LLM deployment patterns and API-based model integration.
• Experience with cloud, particularly AWS.
• Jira, Confluence, ServiceNow experience

Preferred

• Experience supporting AI/ML workloads in production.
• Experience with GPU workloads, autoscaling, and cost optimization.