Staff Software Engineer, Infrastructure

About the Company

Wisdom blends industry expertise with advanced technology to make dental practices work better for everyone involved. We match administrative teams with expert billers and custom-built technology to take on the heavy lifting of dental billing while maximizing dentists’ time in-office and their bottom line.

Responsibilities

• Set the reliability strategy for the platform, including SLOs, error budgets, and operating standards
• Own end-to-end observability using tracing, metrics, logging, and alerting
• Define operational patterns for AI-powered agentic workflows, including retries, backpressure, and capacity controls
• Own deploy and release engineering using Infrastructure as Code (Terraform)
• Build and lead the incident practice, including on-call rotations and blameless post-incident culture

Requirements

• 8+ years of experience running production systems at staff or principal scope
• Deep experience with AWS (or GCP), Terraform, containers (ECS/Kubernetes), and CI/CD
• Hands-on experience operating major LLM APIs (OpenAI, Anthropic, or Google Vertex AI) in production
• Strong command of TypeScript/JavaScript and relational databases

Preferred Qualifications

• Experience operating LLM/agentic systems with frameworks like Mastra, LangChain, or LlamaIndex
• Working knowledge of HIPAA compliance in a healthcare context
• Experience building reliability functions from scratch at a Series A or early-stage startup