Senior Software Engineer - AI Reliability & Observability

Cisco; Milwaukee (WI); Hybrid; USD 150,000 - 250,000; Full time

Job summary

Cisco is seeking a Senior Software Engineer in Application Reliability in the US hybrid model, with focus on reliability and observability for AI-powered applications. You will own feature uptime, instrumentation, and data-driven diagnostics across APIs, agents, and user-facing features.

Join a team building LangGraph-based agents, Looker dashboards, and robust remediation workflows on GCP with BigQuery and BigTable, collaborating across engineering, security, and product teams.

Qualifications

• 7+ years of software engineering with focus on reliability, observability, or production operations.
• Strong Python development skills, with production tooling and automation experience.
• Production GCP experience — deploying on GKE, deep BigQuery SQL, and BigTable expertise.
• Proven experience designing and operating application-level SLI/SLO frameworks and burn-rate alerting.
• Strong debugging skills: distributed tracing, structured logs, and dependency mapping.

Responsibilities

• Define, implement, and enforce feature-level SLIs, SLOs, and error budgets for APIs, AI agents, and apps.
• Build and maintain Looker dashboards on BigQuery/BigTable for real-time observability.
• Design LangGraph-based agents for automated diagnostics and remediation workflows.
• Develop agent evaluation Harnesses to benchmark performance and regression test evolving agents.
• Write complex BigQuery SQL for usage analytics and operational insights.
• Lead incident response and blameless postmortems focused on feature impact.

Skills

Python development

Reliability engineering

Observability

SQL (BigQuery)

GCP / GKE

BigTable

Debugging

Distributed tracing

Education

Bachelor's/Master's in CS/Engineering

Tools

Looker

BigQuery

BigTable

LangGraph

Kubernetes (GKE)

Job description

Cisco is seeking a Senior Software Engineer in Application Reliability in the US hybrid model, with focus on reliability and observability for AI-powered applications. You will own feature uptime, instrumentation, and data-driven diagnostics across APIs, agents, and user-facing features.

Join a team building LangGraph-based agents, Looker dashboards, and robust remediation workflows on GCP with BigQuery and BigTable, collaborating across engineering, security, and product teams.