Site Reliability Engineer (Remote) - #35039

Job Description

Technology Stack:

Backend: Go microservices (Cloud Run/GKE), Python AI agents (GKE/Celery), Temporal workflow orchestration

AI/ML: Agentic ReAct patterns, skill-based agent architecture, MCP tool servers, LiteLLM proxy (Gemini, Claude, GPT), FHIR medical records processing

Frontend: Vue.js 3 + Vuetify

Infra: GCP — AlloyDB PostgreSQL, Cloud Run, GKE, Pub/Sub, Cloud Healthcare, GCS, Memorystore Redis, Terraform, Kustomize

Integrations: Fax.Plus (fax), Mailgun (email), Twilio (SMS/voice), Firebase Auth, health data exchange networks, CMS (for example, Filevine) and CRM platform integrations

Brief Description about the role

Technical Support / Ops Engineer — Monitors and troubleshoots the running platform. Reads Cloud Run logs, Temporal workflow UI, GKE pod status, Pub/Sub queues. Can triage whether an issue lives in the agent (Python), workflow (Temporal), API (Go), or UI (Vue). Handles paralegal-facing issues like stuck cases, failed faxes, pending qualifications. Comfortable with SQL against AlloyDB. Writes runbooks and escalation procedures. Legal ops or litigation support background is a bonus.