Role Description The Compute team's mission: any engineer, using AI, should be able to stand up and operate a stateful service at production scale with no meaningful infrastructure knowledge required. We build the tiering zones, guardrails, and AI skills that make this possible. Reliable, observable, and self-service by design. This is a software engineering role. You'll spend real time writing code: - Platform APIs - Internal tooling - Deployment pipelines - Automation that replaces support tickets Infrastructure fluency matters; infrastructure specialization is not the lead. What matters most is product instinct: - Understanding your users (product engineers) - Measuring whether they're getting unblocked - Treating developer experience as a feature acceptance criterion The platform is yours to own, not just build: - When ArgoCD fails and every team's deploy is blocked, that's your page. - When a product engineer can't figure out why their service is OOMKilling and there's no useful error surface, that's your design failure to fix. A Senior engineer will help define the platform's interfaces and own how product teams interact with compute infrastructure. The team is still establishing its patterns, and you'll have real influence over what they become. What you'll do at Persona: - Build internal platform tooling and APIs that product engineers use to deploy, scale, and observe services, with developer experience as a first-class requirement. - Own and evolve the Kubernetes platform, ArgoCD deployment pipeline, and Terraform IaC that underpin every service at Persona. - Improve platform observability so "why is my service slow" and "why did my deploy fail" have self-service answers. Instrumentation is a platform primitive, not a per-service afterthought. - Drive Cloud Run-to-Kubernetes migration, working directly with product teams to remove blockers and hand off operational ownership cleanly. - Design self-service workflows to reduce the Compute interrupt load. Success means product engineers can do more without filing a ticket. - Define the interfaces and abstractions the platform exposes to product teams. What does "easy to use correctly" look like for a deployment workflow or platform API? Qualifications - Strong SWE fundamentals: shipped production services, writes readable and operable code, can debug distributed system failures across layers you don't fully own. - Product instinct: you measure adoption, treat low usage as a design failure, and change things based on user feedback rather than your own assumptions. - Developer experience sensibility: you identify friction in CLIs, APIs, and deployment workflows and design for clear affordances, actionable error states, and progressive disclosure. - Kubernetes in practice: you've operated services on K8s, can debug scheduling failures, write RBAC policies, and work out why a pod won't start. You're willing to be paged for the platform you build. - Infrastructure as code in a team context: you've modified production IaC alongside other engineers and understand why declarative infrastructure and change safety matter. - Senior candidates: we look for production-level Terraform ownership, including state, module composition, and clean infrastructure refactors. Nice to haves - Deep K8s internals: cluster lifecycle, admission controllers, custom controllers/operators. - ArgoCD or another GitOps tool in production. - GKE or managed Kubernetes at scale. - Ruby or Rails (we integrate with Ruby systems). - Experience in a regulated or high-trust environment. Benefits - Medical, dental, and vision insurance. - 3% 401(k) contribution. - Unlimited PTO. - Quarterly mental health days. - Family planning benefits. - Professional development stipend. - Wellness benefits.