Staff Software Engineer, Infrastructure

Staff Software Engineer

The roadmap isn't handed to you here. You'll help write it, then build the parts that matter most.

As a Staff Software Engineer at Wisdom, you'll set technical direction across the platform and build the systems that automate dental insurance billing end to end: the LLM-driven agents that make high-stakes billing decisions, the integrations that keep inconsistent insurance and practice-management systems talking to us, the product our customers use every day, and the infrastructure it all runs on. This is a force-multiplier role on a small, high-trust team. You'll go where the hardest, highest-leverage problem is, whether that's a gnarly product feature, a brittle carrier integration, an AI pipeline that needs to fail safe instead of loud, or the deploy path the whole team depends on, and you'll leave both the codebase and the team better than you found them.

Wisdom's stack is TypeScript, Node.js, React, Postgres, and AWS, with LLM-driven agents (Mastra, Anthropic) making high-stakes billing decisions in production. The problems we're solving are legitimately hard: keeping inconsistent insurance integrations alive, making AI pipelines fail safe instead of failing loud, and running HIPAA-compliant systems that genuinely can't go down. We'd rather have someone energized by owning problems end to end than someone who wants a narrow lane and a perfect brief.

In your first year, you'll have shipped platform-defining work across the stack, raised the technical bar through the code and standards you set, and become the person the team routes its hardest problems to. This is a fully remote role reporting directly to the Head of Engineering.

What You'll Own

• Set technical direction across the platform: the architecture, the standards, and the roadmap for systems that bill real money for real practices, plus the judgment about what to build, what to buy, and what to leave alone.

• Build across the whole stack: ship product features, backend services, and the data layer end to end. You're as comfortable in a React component as in a Postgres query plan or an AWS deploy.

• Own how we build and operate AI-powered agentic workflows: the pipelines where LLMs make billing decisions in production, including retries, idempotency, graceful degradation, and cost and capacity controls. The failure modes here are new (batch blowups, stream drops, runaway cost, model misbehavior), and you'll set the patterns the team builds against.

• Harden the integration surface with dental insurance carriers and practice-management systems (Dentrix, Eaglesoft): poorly documented, inconsistent, and the first thing to buckle under load.

• Keep production healthy: fast, safe, reversible deploys, observability that surfaces problems before users do, and an incident practice that runs without heroics. Reliability is everyone's job here, and you'll make it easy to do well.

• Raise the bar through others: set technical standards via code review, architecture guidance, and documentation that actually gets used, and level up how the whole engineering team reasons about building and operating software.

• Take on the ambiguous, undefined, company-level problems and drive them to resolution without waiting for permission or a perfect brief.

Who You Are

• 8+ years building and operating production software, with a track record of operating at staff/principal scope. You've owned systems where the work had real consequences and left them measurably better.

• You've shipped across the stack: product features, backend services, and the infrastructure underneath, and you can reason from first principles when the runbook runs out.

• You multiply the people around you. Your impact shows up in what others ship, not only in what you touch directly. You've set standards, mentored engineers, and driven technical decisions across teams without needing the authority to mandate them.

• Strong command of TypeScript/JavaScript, across both application code and the systems around it. You can go deep wherever the problem is.

• Deep AWS (or GCP) experience. You've deployed, operated, and debugged distributed services in production.

• Deep experience with relational databases: connection management, query performance, and reasoning about data integrity under load.

• Hands-on production experience with at least one major LLM API (OpenAI, Anthropic (Claude), or Google Vertex AI), with a feel for the operational reality: rate limits, retries, latency, cost, and what happens when the model misbehaves in a live system.

• You default to ownership and move toward the hard problem, not away from it.

• You're direct, intellectually honest, and collaborative. You surface bad news early, change your mind when the evidence warrants it, and write the postmortem that makes the whole team sharper.

You'll Stand Out If You Have

• Experience building or operating LLM / agentic systems in production, or with frameworks like Mastra, LangChain, LlamaIndex, or CrewAI, where reliability, cost, and latency were yours to manage.

• Comfort with infrastructure as code (Terraform), containers (ECS/Kubernetes), and CI/CD. You don't need to be an SRE, but you're not afraid of the deploy path.

• Working knowledge of HIPAA compliance and what it means to build responsibly in a healthcare context.

• Experience at a Series A or early-stage startup where you built things from scratch rather than inheriting them.

Wisdom is an equal opportunity employer. We provide employment opportunities without regard to age, race, color, ancestry, national origin, religion, disability, sex, gender identity or expression, sexual orientation, veteran status, or any other protected status in accordance with applicable law.