Senior Software Engineer – Application Reliability (Kubernetes, GCP, SQL), Hybrid
Core
Own the reliability of AI-powered applications and features, focusing on feature uptime, automated diagnostics, and self-healing remediation at the application layer.
Role type
Senior Software Engineer (Application Reliability)
Builds
LangGraph-based agents for automated diagnostics, Looker dashboards for observability, and evaluation harnesses for agent quality.
Domain
Generative AI, Cloud Infrastructure, Application Reliability
Deliverable
production ML models | product features | dashboards & analysis
Required skills
Python, Kubernetes (GKE), BigQuery, BigTable, SQL, SLI/SLO design, distributed tracing, agent engineering
Preferred skills
Agent evaluation harnesses, A2A protocols, feature flags, GCP observability services, AIOps, GenAI application development, Looker
Technologies
LangGraph, Looker, BigQuery, BigTable, Python, GCP, Kubernetes
Responsibilities
Define and enforce feature-level SLIs/SLOs/error budgets; Build application observability systems with Looker dashboards; Design LangGraph agents for automated issue identification and remediation; Develop agent evaluation harnesses; Write complex SQL for usage trend analysis; Lead application-level incident response and postmortems; Build Python tooling to reduce MTTD/MTTR.
Seniority
Senior, hands-on IC