Staff Full-Stack Engineer, AI/LLM

ABOUT TOMORROW HEALTH

Tomorrow Health enables exceptional healthcare for patients and their families in the place they want to be most — home. At Tomorrow Heath, we build technology that rewires the way home-based care is ordered, delivered, and paid for. Tomorrow Health connects patients, providers, health plans, and home-based care suppliers, to ensure patients receive the correct and timely care they need to remain healthy at home.

We believe that a team’s strength is in its people. Our goal is to raise the industry standard for patient experience, and we realize this cannot be achieved without a team that reflects the vast diversity in race, ethnicity, gender, sexuality, and set of experiences and perspectives of the patients we serve. We believe in putting patients first, that many perspectives are stronger than one, and in treating those we serve just as we would our own family members. If you’re passionate about improving healthcare delivery, leveraging technology to serve people, and working in a collaborative, diverse environment, we hope you’ll join us.

THE TEAM

The Engineering team at Tomorrow Health builds the technology that connects and scales the home health ecosystem in order to transform the home into the preferred place of care for positive patient outcomes. Our products serve a diverse set of users – doctors, insurance companies, medical equipment suppliers – and ultimately enable us to deliver a higher quality patient experience. Our team of mission-driven technologists is highly collaborative, supportive, empathetic, curious, and impact-oriented. We partner with the Product, Operations, and Customer Experience teams to identify opportunities to enable a faster, simpler, and more transparent process for patients and healthcare partners. 

THE ROLE 

Tomorrow Health is seeking a Staff Full Stack Software Engineer with deep backend expertise and a proven track record in working with Large Language Models (LLMs). This role is pivotal to driving our AI-first strategy, helping evaluate, integrate, and operationalize cutting-edge models into core product experiences. As a Staff Engineer, you will lead technically across the stack, but with a critical lens toward how AI can shape our workflows, decision-making, and patient outcomes.

You’ll report to the Engineering Manager and collaborate closely with Product, Data, and Clinical teams to deliver high-impact platform capabilities. You’ll also play a central role in LLM-based feature design, model evaluation, and the implementation of production-grade AI services.

Please note: this is a hybrid-role which will require this team member to work out of our New York City office 4 days per week.

WHAT YOU'LL DO

• Lead technical design and architecture for AI-powered product features, ensuring scalability, maintainability, and clinical safety.
• Evaluate and integrate LLM platforms (e.g., OpenAI, Anthropic, open-source models), shaping model selection, prompt frameworks, and performance benchmarking.
• Design and implement robust backend systems (Python/Django) and scalable APIs to support AI-first features across the platform.
• Work across the stack (React/TypeScript/NodeJS) as needed to deliver full product experiences.
• Collaborate with cross-functional stakeholders to align AI initiatives with business and clinical goals, especially around new payor onboarding and integrations.
• Partner with data engineers and ML practitioners to ensure proper data pipelines, feedback loops, and real-world performance monitoring for AI models.
• Build internal tools and observability features to measure the impact and safety of AI models in production.
• Mentor engineers across the org on best practices for software engineering and AI integration.

ABOUT YOU

• 8+ years of experience building and scaling customer-facing software; deep backend expertise (Python/Django) required.
• Proven experience evaluating, integrating, and/or deploying LLMs or similar foundation models in a production environment.
• Strong understanding of LLM performance considerations: token limits, latency tradeoffs, prompt engineering, fine-tuning, and guardrails.
• Strong system design skills and experience with APIs (REST/GraphQL), relational databases (Postgres), and cloud platforms (AWS preferred).
• Familiarity with modern frontend technologies: React, TypeScript, and NodeJS.
• Strong cross-functional collaboration and communication skills — able to simplify complex AI concepts for stakehol