> Markdown version of [/jobs/ext/4564820-engineer-claims-platform](https://www.wearedevelopers.com/jobs/ext/4564820-engineer-claims-platform). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Engineer, Claims Platform - **Company:** RECOURSE HEALTH LLC - **Location:** San Francisco, CA, United States - **Experience:** Experienced - **Contract:** Permanent contract - **Skills:** Artificial Intelligence, Application Integration Architecture, Audit Trail, Spreadsheets, Software as a Service, Electronic Data Interchange (EDI), Design of User Interfaces, Human-Computer Interaction, PostgreSQL, Node.Js, Prism (Software), Next.js, SQL Databases, TypeScript, Workflow Management Systems, Google Cloud, Data Ingestion, Fast Healthcare Interoperability Resources, Large Language Models, State Machines, Backend, Health Level Seven International, Front End Software Development, Api Design, Crud - **Published:** November 4, 2026 - **Apply:** https://www.careerbuilder.com/job-details/engineer-claims-platform-san-francisco-ca--43b6ebbc-0109-4acb-87c9-a4bf1492a555 ## About the Role Healthcare, Spreadsheets, Time Management, User Interface/Experience (UI/UX), Litigation, Finance, Theater, Product Engineering, Machine Tool, Artificial Intelligence (AI), You are a strong generalist. Comfortable jumping between backend, frontend, data, and AI integration. You may not be an expert in every layer, but you pick up what you need to ship the thing. You are AI-pilled. You've used AI tools to ship real work and you have opinions about which ones are useful and which are hype. You stay current because the world is changing and you want to see the next shift before anyone else. You have a bias to action. You don't default to no. Speed of iteration over polish of iteration. You start, you learn, you fix things in motion. Most decisions are reversible and do not need extensive study. You care about the craft. You write code you would be comfortable handing to anyone else. You think about the reader of your code, not just the compiler. You leave the codebase better than you found it. You are intellectually honest. You ask questions when you don't understand something. You say so when you're wrong. You use plain language. You respectfully challenge decisions you disagree with, and once a decision is made, you commit. You put the team first. You are reliable and fully invested. You take your vacations. You check on your teammates. You help build a culture where people do their best work because they are supported, not squeezed. What You Bring * 4+ years building and shipping production software, full-stack exposure preferred * Comfort with TypeScript, Node, a modern frontend framework, and SQL. The specific stack matters less than the ability to pick things up * Meaningful hands-on experience integrating LLMs into real products, not just trying the playgrounds * Strong instincts for data modeling, API design, and the difference between a clean abstraction and an over-engineered one * Experience building in regulated or security-sensitive environments (HIPAA, SOC 2, PCI, financial controls) is a plus * A preference for small teams and early-stage chaos over mature org charts Strong plus, not required: healthcare data experience (claims, EDI, HL7/FHIR, clearinghouses). We'll teach the domain to the right person. Sound judgment, technical depth, and ownership mindset are required. Grit matters more than pedigree. ## Description Build the system that moves a claim from a messy remittance file to money in a provider's account. Why This Exists A federal arbitration system called Independent Dispute Resolution, or IDR, now determines billions of dollars in healthcare payments each year. Providers win the vast majority of disputes, yet most eligible claims are never filed. The process is manual, fragmented, and resource-intensive, and most providers don't have the infrastructure to pursue what they're owed. The No Surprises Act created the framework, and the market already exists. Today it runs on spreadsheets, consultants, and static playbooks. We're building the first intelligent system designed to operate inside it. The platform is the company. Every claim moves through an eight-stage workflow, from intake through eligibility, evidence packaging, submission, and resolution. When it works, providers get paid. When it breaks, they don't. Why This Is Hard (and Interesting) This is not clean CRUD SaaS. Claims data is inconsistent and domain-heavy. Payers adapt. Deadlines cascade, and missing one loses a case on procedure regardless of merit. Audit trails matter because this is a regulated environment handling PHI. The same EOB parsed twice needs to produce the same answer, every time, or the whole thing is untrustworthy. You'll work across the stack: data ingestion, LLM-powered reasoning, workflow orchestration, and product UI. Not siloed into one layer. And the system has to be right. A bug here doesn't degrade an experience, it costs a provider real money or gets a dispute thrown out., You'll build the core claims platform alongside our Head of Engineering. You will: * Ship features across the stack: backend services, LLM integrations, workflow orchestration, and product UI * Own pieces of the eight-stage claim workflow and the state machine that drives it * Build the eligibility engine, the logic that decides whether a claim can go to arbitration at all * Work directly with the people running claims. Their feedback is your backlog, and they sit next to you * Build for a regulated environment where correctness, auditability, and financial impact are tightly coupled * Take real ownership of production: observability, quality, and fixing what breaks * Use AI tooling as a core part of how you ship, not as a novelty We build with Claude Code daily and run a Codex review pass on every slice. The stack is TypeScript, Next.js, Prisma, and PostgreSQL on Google Cloud, with LLM reasoning throughout., You'll ship product that moves money for real providers, and you'll see it happen. Not a metric on a dashboard. Actual dollars recovered for a hospital that had written them off. You'll also work in a domain that's genuinely interesting to build in. Adversarial counterparties, cascading deadlines, messy real-world data, and a decision engine where intelligence directly determines financial outcomes. Very few product problems have that shape. If you want this to be the most memorable stretch of your career, where you shipped something real, with a team you respected, in a domain that actually matters, this is the seat. Please apply even if you don't fit 100% of these requirements. We would like to talk.