Lead DevOps Engineer

Responsibilities

• Lead the architecture and maintenance of the infrastructure and reliability practices that keep AI‑powered systems performant, observable, and trustworthy under real production load, including redundancy, latency, and cost management.
• Help define SLOs/SLIs for AI‑powered services, including latency and quality SLOs for LLM inference paths, and build the error‑budget discipline that lets product teams ship fast without breaking trust.
• Design scalable, secure infrastructure for distributed AI services, event‑driven workloads, and multi‑LLM‑provider integrations.
• Build metrics, tracing, and alerting that surface not just "is it up" but "is it behaving correctly" for LLM‑powered features (drift, regression, hallucination rates, tool‑call failures).
• Define and enforce PRR‑style standards across teams launching new AI products and features.
• Mentor engineers, drive architecture reviews, and shape the broader engineering culture around reliability.

Requirements

• Significant infrastructure engineering experience combining DevOps and SRE disciplines at scale.
• Deep GCP expertise (AWS a strong plus); relevant cloud certifications welcome.
• Production experience with SRE fundamentals: SLO/SLI design, error budgets, toil reduction, blameless incident review.
• Strong background in distributed systems failure modes and resilience patterns.
• Expert‑level infrastructure‑as‑code (Terraform), container orchestration (Kubernetes), and CI/CD.
• Hands‑on with modern observability stacks (i.e., OpenTelemetry, Sentry) and AI‑specific observability tooling (Arize, LangSmith, Braintrust, or similar).
• Experience with API management platforms, particularly Apigee and Cloud Run.
• Comfort working across Python, Javascript, and Bash for infra tooling.
• Strong spoken and written communication in English with teams and stakeholders.