Senior Agentic AI Production Reliability Engineer (Remote)

Ema Unlimited; Lingfield; Remote; GBP 70,000 - 100,000; Full time

Job summary

Ema Unlimited is seeking a Senior Technical Support Specialist to own the health, reliability, and trust of our agentic AI systems deployed in production. You will act as an operator of live AI systems, not a ticket handler, with authority during incidents and a focus on preventing major outages.

You will partner with Engineering, Product, and Implementation to diagnose failures, improve data quality, and ensure robust RCA-driven fixes.

Qualifications

• 6–9+ years in senior technical support, reliability, or production engineering roles.
• Experience with AI/automation platforms and live AI systems.
• Familiarity with major cloud providers (AWS, GCP, Azure).

Responsibilities

• Diagnose failures in multi-agent AI workflows and explain AI behavior clearly.
• Manage platform configuration, data quality, and escalation workflows.
• Collaborate with Engineering, Product, and Implementation to prevent incidents and drive RCA actions.
• Escalate to the right teams and keep customers informed with calm, factual communication.
• Contribute to on-call readiness and improve incident response processes.

Skills

Senior support

AI systems

Cloud platforms

Incident response

RCA

Reliability engineering

Cross-functional

On-call

Tools

AWS

GCP

Azure

Job description

Ema Unlimited is seeking a Senior Technical Support Specialist to own the health, reliability, and trust of our agentic AI systems deployed in production. You will act as an operator of live AI systems, not a ticket handler, with authority during incidents and a focus on preventing major outages.

You will partner with Engineering, Product, and Implementation to diagnose failures, improve data quality, and ensure robust RCA-driven fixes.