Recourse is seeking an AI Engineer, Decision Intelligence to own the intelligence layer of our product in a regulated, adversarial environment. This office-based role in San Francisco, United States will build the decision engine that determines which claims to contest and at what offer amount, design the LLM systems that generate arguments (medical necessity, patient acuity, market comparables, full submission), and establish evaluation infrastructure with golden datasets and offline evals to measure real outcomes. You will architect the balance between deterministic rules and model reasoning, close the feedback loop from arbitration outcomes, and build for explainability so every recommendation has defensible reasoning. You will collaborate with operations and payer strategy to surface patterns in claims early. The stack includes TypeScript, Next.js, Prisma, and PostgreSQL on Google Cloud, with LLM reasoning woven throughout. Requirements include 5+ years of engineering experience with production ML/LLM-powered systems, strong evaluation experience, comfort shipping end-to-end, and a track record in regulated environments (HIPAA, SOC 2, PCI) is a plus. Healthcare data experience is a plus; otherwise we’ll teach you. If you’re analytical, action-oriented, and eager to impact a real-world product that recovers dollars, this is the seat for you.

Recourse is seeking an AI Engineer, Decision Intelligence to own the intelligence layer of our product in a regulated, adversarial environment. This office-based role in San Francisco, United States will build the decision engine that determines which claims to contest and at what offer amount, design the LLM systems that generate arguments (medical necessity, patient acuity, market comparables, full submission), and establish evaluation infrastructure with golden datasets and offline evals to measure real outcomes. You will architect the balance between deterministic rules and model reasoning, close the feedback loop from arbitration outcomes, and build for explainability so every recommendation has defensible reasoning. You will collaborate with operations and payer strategy to surface patterns in claims early. The stack includes TypeScript, Next.js, Prisma, and PostgreSQL on Google Cloud, with LLM reasoning woven throughout. Requirements include 5+ years of engineering experience with production ML/LLM-powered systems, strong evaluation experience, comfort shipping end-to-end, and a track record in regulated environments (HIPAA, SOC 2, PCI) is a plus. Healthcare data experience is a plus; otherwise we’ll teach you. If you’re analytical, action-oriented, and eager to impact a real-world product that recovers dollars, this is the seat for you.