AI-Powered Production Reliability Engineer

Cisco Systems, Inc; Greater London; Hybrid; GBP 90.000 - 150.000; Vollzeit

Zusammenfassung

Cisco Systems, Inc is seeking a Software Engineer to design and deploy AI-powered production intelligence capabilities at scale. You will combine Site Reliability Engineering with agentic AI to monitor, diagnose, and auto-remediate global SaaS infrastructure.

You will build AI agents, integrate MCP tooling, and implement end-to-end telemetry across distributed systems, driving reliability and rapid incident response.

Qualifikationen

• Experience delivering distributed, high-availability SaaS platforms at scale.
• Strong proficiency in Python, Go, Java, or C++ with microservices experience.
• Deep Kubernetes/Docker experience in large multi-cluster environments.

Aufgaben

• Design and implement high-resilience software for AI-assisted observability and self-healing infra.
• Build AI agents, MCP tooling, and deterministic evaluation pipelines.
• Implement ingestion/correlation across logs, metrics, and traces to speed MTTD/MTTR.
• Develop safe production automation with guardrails and HITL workflows.
• Partner with teams to define SLIs/SLOs and lead PIRs.

Kenntnisse

Python

Go

Java

C++

Kubernetes

Docker

SRE practices

OpenTelemetry

ML/AI tooling

Ausbildung

Bachelor's degree in Computer Science or related field

Master's/PhD preferred for senior roles

Tools

Prometheus

Grafana

Kafka

Redis

Elasticsearch

Jobbeschreibung

Cisco Systems, Inc is seeking a Software Engineer to design and deploy AI-powered production intelligence capabilities at scale. You will combine Site Reliability Engineering with agentic AI to monitor, diagnose, and auto-remediate global SaaS infrastructure.

You will build AI agents, integrate MCP tooling, and implement end-to-end telemetry across distributed systems, driving reliability and rapid incident response.