Founding Engineer (Fullstack/AI)

Role Overview

Our small product squad (2 fullstack engineers + PM) ships quickly, but customer demand is growing faster than we can build. We’re looking for a senior, product‑minded engineer who can wear many hats — architecture, data, fine-tuning & RAG, with a bit of product taste — and help lay the technical and cultural foundations of the company.

What You’ll DoOwn features end‑to‑end: design, build, ship, and iterate on backend services, web front‑end, and internal tooling.

Scale our Gen‑AI stack: productionize retrieval‑augmented generation pipelines, implement evaluation harnesses, and harden monitoring/alerting.

Shape engineering culture: introduce best‑in‑class CI/CD, code quality standards, security, and mentoring practices.

Collaborate: work with product and sales to translate real patient pain points into elegant solutions.

Influence roadmap: participate in product discovery, weigh technical trade‑offs, and keep us focused on what moves the needle.

Required Technical Skills

• Our core technologies: Python, Postgres, MySQL, NextJS, LangSmith, AWS. We're flexible—use the right tool for the job.
• 5+ years building and operating production software
• U.S. work authorization & residency required
• Proven experience shipping LLM or conversational‑AI products at scale (LLM‑APIs, vector stores, agent frameworks)
• Proficiency in Python and modern JavaScript
• Familiarity with SQL and schema design
• Comfort with cloud infrastructure (AWS preferred) and infrastructure as code (IaC)
• Working knowledge of agents, vector search, embeddings, and RAG performance tuning
• Product taste: you sweat the UX details
• Good communication skills: you can explain complex trade‑offs to non‑engineers

Nice-to-Haves

• Prior healthcare experience
• Understanding of HIPAA, SOC‑2, or other security/compliance frameworks
• Performance and cost‑optimization of ML workloads