Senior Software Engineer – Llm

About Health Note

Health Note is building AI-powered digital assistants that act like trusted members of the care team. Instead of rigid, disconnected software modules, our assistants gain skills over time — from handling simple reschedules to managing complex intake, referrals, and medication refills. Patients experience a natural, empathetic interaction, while providers gain a system that is reliable, transparent, and continually improving. Our goal is to deliver a concierge experience for every patient, and a scalable path to automation for every clinic.

About the Role

This role is an opportunity to join a high-impact team with tremendous growth opportunities. As a Senior Software Engineer, you will be responsible for developing and maintaining mission-critical systems that power healthcare operations and interoperability for over 60 clinics and health systems.

At Health Note, we’re not building new AI models — we’re using services to deliver digital assistants that act like trusted members of the care team. These assistants grow new skills over time, handle complex patient-facing workflows safely and reliably, and transform healthcare operations into a continuous improvement process. The result is not just reliable automation, but a human and empathetic experience that patients and providers trust.

As part of a cross-functional team, you’ll collaborate with product managers, solution engineers, and client experience managers to create world-class, AI-enabled solutions. You’ll shape architectural decisions, integration patterns, and developer workflows so that AI isn’t just “bolted on,” but thoughtfully incorporated into our platform.

This opportunity is ideal if you want to take the next step in your career and join a growth-stage organization focused on healthcare — while working at the frontier of AI-enabled software development.

We’re a fully distributed, remote-first, fast-growing startup. Our engineering team is spread from UTC-3 to UTC-7 and we rely heavily on strong asynchronous communication. Occasionally, you’ll need to flex to sync up with teammates across time zones.

Our cutting-edge stack is full-stack TypeScript leveraging NestJS, React, Remix, Tailwind, GraphQL, PostgreSQL, Redis, Pulumi, all on AWS. Our architecture is service oriented and managed in a Monorepo.

Responsibilities

• Design, implement, and maintain highly scalable and performant services and applications.
• Integrate LLMs and AI services into production systems, with attention to safety, observability, performance, and cost effectiveness.
• Build abstractions, APIs, and internal tooling that make it easier for other engineers and product teams to leverage AI responsibly.
• Continually improve the codebase and test coverage through refactoring, automated testing, CI / CD, and strong developer productivity practices.
• Experiment with emerging AI technologies and evaluate their fit for our products, balancing speed-to-market with reliability.
• Mentor and support other engineers, setting coding standards and architectural practices that ensure long-term maintainability.
• Collaborate with cross-functional teams to design AI-enabled product experiences that meet real client needs.

Qualifications

• 5+ years of experience building robust, scalable full-stack applications, databases, and developer tools.
• Hands-on experience working with LLMs or AI services (e.g., OpenAI, Anthropic, Vertex AI, Llama) in a professional or personal capacity.
• Significant experience designing, building, deploying, and maintaining production applications at scale.
• Proficiency with Javascript / Typescript, React, NodeJS (NestJS), and PostgreSQL.
• Familiarity with modern web technologies (HTTP2, WebSockets, gRPC, GraphQL).
• Comfort architecting solutions to ambiguous problems with significant impact.
• Experience leaving the codebase better than you found it through automated testing, CI / CD, and observability.

Nice to Haves

• Experience designing evaluation frameworks for AI-enabled features (e.g., measuring quality, accuracy, and reliability of LLM outputs).
• Familiarity with RAG, embedding algorithms, and intent classification.
• Experience with observability and monitoring systems (Langfuse, Datadog, Grafana, Sentry, CloudWatch, etc.).
• Experience with infrastructure-as-code in production.
• Familiarity with internal UI and integration tools (ReTool, Salesforce Communities, Contentful, NextJS, etc.).
• Experience with containers and orchestrators like Docker or Kubernetes.
• Background in healthcare, regulated industries, or EHR / EMR integration.
• Experience debugging distributed systems.

You do not need to have prior experience with every technology in our stack. We believe great candidates are capable of learning new tools quickly, and we provide mentorship and guidance as needed.

We offer :

• We welcome new ideas and allow you to make an immediate impact on the team.
• Flexible paid time off (PTO for any reason, including sick days, with no specified limits) and flexible work schedule.
• Personal laptop.
• Health / Sport Budget.
• Fully remote.