Senior Software Engineer – Reliability; Kubernetes, GCP, SQL), Hybrid

Senior Software Engineer In Application Reliability

This position is based in San Jose, CA or North Carolina and operates under a hybrid work model.

Join Cisco's Enterprise AI team, the core group enabling Generative AI powered experiences across Cisco. Our mission is to build secure, scalable AI platforms that empower teams to safely develop, deploy, and operationalize AI-powered solutions. We operate at the intersection of applied AI, cloud infrastructure and security — partnering across engineering, security, compliance, and product teams to bring trusted AI to life at an enterprise scale.

We are a fast-growing, highly collaborative team of platform engineers, AI engineers, and data scientists who value technical depth, ownership, and pragmatic execution. What makes this team exciting is the opportunity to define how secure Generative AI is built and governed inside a global technology leader.

As a Senior Software Engineer in Application Reliability, you will own the reliability of our AI-powered applications and features from the user's perspective. While our infrastructure SRE team ensures the platform is healthy, your focus will be on feature uptime, usage trends, automated issue identification, and self-healing remediation at the application layer. You will build Lang Graph-based agents for automated diagnostics, Looker dashboards for observability, and evaluation harnesses for agent quality - all powered by Big Query, Big Table, and Python.

You will partner closely with application developers, data engineers, and infrastructure SREs to ensure our APIs, RAG systems, agents, and user-facing features are reliable, observable, and continuously improving.

• Define, implement, and enforce feature-level SLIs, SLOs, and error budgets for APIs, RAG systems, AI agents, and user-facing applications.
• Build and maintain application observability systems using Looker dashboards on Big Query and Big Table — providing real-time visibility into feature health, error patterns, and usage trends for developers, PMs, and leadership.
• Design and build Lang Graph-based agents for automated issue identification and remediation: anomaly detection on BQ logs, root cause diagnosis, auto-rollback, feature flag kill switches, and self-healing workflows.
• Develop agent evaluation harnesses to benchmark agent performance, test multi-step workflows, handle non-deterministic outputs, and run regression testing as agents evolve.
• Write complex SQL (Big Query) for usage trend analysis, anomaly detection, and operational analytics; design BQ table schemas optimized for observability and debugging.
• Analyze application usage trends and adoption metrics to proactively identify reliability risks, capacity needs, and degraded user experiences before they become incidents.
• Partner with application development teams to embed reliability practices into the development lifecycle: deployment safety (canary, progressive rollout), structured logging standards, and distributed tracing.
• Lead application-level incident response, root cause analysis, and blameless postmortems focused on feature impact rather than infrastructure symptoms.
• Build Python-based tooling and automation to reduce mean time to detect (MTTD) and mean time to resolve (MTTR) for application-layer issues.
• Stay current with the rapidly evolving AI landscape (new frameworks, tools, and paradigms) and apply emerging techniques to improve platform reliability and developer productivity.

• 10+ years of experience in software engineering with significant focus on reliability, observability, or production operations;
  Bachelor's or Master's Degree in Computer Science, Engineering, or a related technical discipline.
• Strong Python development skills, with experience building production tooling, automation, and agent-based systems.
• Production GCP experience — deploying and managing applications on GKE (Kubernetes), deep SQL expertise with Big Query (complex queries, window functions, schema design, cost optimization), and hands-on experience with Big Table (or equivalent) for high-throughput operational data.
• Proven experience designing and operating…