Remote Senior Agentic AI Production Reliability Engineer

Ema Unlimited; Tilbury; Remote; GBP 75,000 - 110,000; Full time

Job summary

Ema Unlimited is seeking a Senior Technical Support Specialist to own the health and reliability of its agentic AI systems in production. You will diagnose failures, explain AI behavior to customers, and partner with Engineering, Product and Implementation to prevent incidents.

This full-time role offers remote work within the United Kingdom, with compensation determined by location, knowledge, and experience.

Qualifications

• 6+ years in senior technical support, reliability, or production engineering roles.
• Experience with AI/automation platforms.
• Familiarity with cloud providers (AWS/GCP/Azure).

Responsibilities

• Diagnose failures in multi-agent AI workflows and agentic systems.
• Explain AI failures in a way customers can understand and guide remediation.
• Collaborate with Engineering, Product and Implementation to prevent repeated incidents.
• Improve on-call hygiene, escalation clarity, and incident communication.
• Contribute to RCA processes and continuous reliability improvements.

Skills

AI systems

Incident response

Root cause analysis

Communication

Tools

AWS

GCP

Azure

Job description

Ema Unlimited is seeking a Senior Technical Support Specialist to own the health and reliability of its agentic AI systems in production. You will diagnose failures, explain AI behavior to customers, and partner with Engineering, Product and Implementation to prevent incidents.

This full-time role offers remote work within the United Kingdom, with compensation determined by location, knowledge, and experience.