Job Description

The Role

We are looking for a Founding AI Engineer to take the lead on our intelligence layer. This isn't a role for running six-month research projects; you will be shipping production-ready LLM features into the hands of clinicians from day one. You will own the entire AI surface area—from architecture and model selection to evals and agent design.

Key Responsibilities

• End-to-End AI Ownership: Own the AI lifecycle including architecture, model selection, evals, and agent design.
• Production-First Mindset: Rapidly improve existing LLM features and ship new ones directly into clinical workflows.
• Full-Stack Implementation: Work across the stack (TypeScript, React Native, NestJS) to ensure AI features are seamlessly integrated into the UI clinicians actually use.
• Solve Unsolved Problems: Address genuine healthcare challenges like AI accuracy, context-awareness, and latency under real clinical constraints.
• Strategic Partnership: Partner with founders to define the AI roadmap and establish high engineering standards.
• Responsibility & Output: Maintain a high quality bar, ensuring all AI-generated or assisted code is fully understood and owned.

Who We Are Looking For

Must Haves

• TypeScript Expertise: Deep proficiency in the language that powers our entire stack.
• AI Production Experience: Proven experience shipping LLM/AI features in a production environment.
• Experience: At least 3 years of full-time professional experience (excluding internships).
• Communication: Ability to articulate complex technical ideas clearly and participate in healthy, ego-free feedback loops.

Preferred Qualifications

• Modern Stack Proficiency: Experience with React Native/Expo, Next.js, NestJS, and PostgreSQL.
• 0→1 Builder: A track record of taking products from concept through production in a startup environment.
• DevOps/CI/CD: Proficiency with containers and cloud deployments (GCP is a plus).
• Mission Alignment: A genuine interest in healthcare/clinical workflows and improving patient outcomes.

Our Core Values

• Open to Feedback: We view code reviews and suggestions as a way to make the product better, not as personal attacks.
• Constructive Disagreement: We encourage speaking up if you see a better path forward; we choose the best solution for the product together.
• Ownership of Output: We have zero tolerance for "AI slop." Whether you wrote it or an AI generated it, once you commit it, you own it. You must fully understand why you are committing a piece of code.
• No Ego: We value humble, down-to-earth collaborators who are hyper-reactive to the needs of the product, not their own status.