Senior Enterprise AI Production Support Engineer

Ema; Manchester; On-site; GBP 70,000 - 120,000; Full time

Job summary

Ema Unlimited Inc. in London is seeking a Senior Support Engineer to own the health, reliability and trust of production agentic AI systems. You will diagnose incidents, coordinate across teams, and provide workarounds to unblock customers while engineering fixes are applied.

You will debug multi-agent workflows, trace failures across integrations and humans-in-the-loop, communicate clearly with customers and engineers, and help shape product reliability through robust RCA and improved runbooks.

Qualifications

• 6–9+ years in senior technical support, reliability, or production engineering roles.
• Experience supporting enterprise SaaS platforms in production.
• Strong understanding of APIs and integrations; distributed systems; logs and diagnostics.
• Experience handling escalations and incidents with senior stakeholders.
• Customer-facing experience with senior stakeholders.
• Preferred background in AI / automation platforms and production reliability.
• Familiarity with workflow orchestration or agentic systems.
• Experience with AWS, GCP or Azure cloud platforms.
• Background in high-availability, 24×7 systems.

Responsibilities

• Own customer-reported issues from intake to resolution adhering to SLAs.
• Diagnose, coordinate, and close incidents; provide workarounds to unblock customers.
• Ensure no issues are lost between teams; act as technical owner across teams.
• Debug agentic workflows end-to-end and trace failures across agents, tools, and humans-in-the-loop.
• Communicate clearly with engineers and customers during incidents.
• Write high-signal bug reports and incident summaries for RCA and product feedback.

Skills

APIs & integrations

Distributed systems

Logs & diagnostics

Customer-facing support

Debugging instincts

Tools

AWS

GCP

Azure

Job description

Ema Unlimited Inc. in London is seeking a Senior Support Engineer to own the health, reliability and trust of production agentic AI systems. You will diagnose incidents, coordinate across teams, and provide workarounds to unblock customers while engineering fixes are applied.

You will debug multi-agent workflows, trace failures across integrations and humans-in-the-loop, communicate clearly with customers and engineers, and help shape product reliability through robust RCA and improved runbooks.