Remote Machine Learning Engineer Biotech Jobs in Maine

LumiMeds is a high-growth telehealth platform building the next generation of virtual telehealth infrastructure. We are looking for an AI-First Full-Stack Engineer who treats AI not as a tool but as a core part of how they think, build, and ship.

This is not a role for someone who occasionally uses Copilot to autocomplete lines. You are an engineer who has rebuilt how you work around AI- using LLMs to generate scaffolding, reason through architecture, write tests, debug production issues, and ship faster than a team twice the size. Critically, you know how to orchestrate Claude agent teams to parallelize complex engineering work, treating a coordinated group of Claude agents as a force multiplier on top of your own output. You will balance 90% hands-on coding with 10% knowledge sharing, and you are expected to push the velocity ceiling of what one engineer can deliver.

You will build and scale the following critical healthcare systems:

• EMR & Clinical Data Engine: Implementing high-availability Electronic Medical Record (EMR) systems with complex data modeling for patient history and clinical notes.
• AI Clinical Copilot: Integrating LLMs to automate clinical documentation, summarize patient charts, and surface actionable insights for providers.
• Prescription Management (e-Prescribing): Building secure, auditable workflows for medication orders, pharmacy integrations, and state-machine-based fulfillment tracking.
• Virtual Care Infrastructure: Implementing real-time patient-provider interfaces, including WebRTC video, secure messaging, and async consultation flows.
• E-commerce & Checkout: Engineering high-conversion storefront experiences, including complex product catalogs, subscription billing models, and dynamic pricing engines.

• AI-Augmented Development: Use Cursor, Copilot, and LLM APIs as first-class engineering tools - not as an afterthought. Generate, validate, and iterate on code at machine speed.
• Claude Agent Team Orchestration: Design and operate teams of Claude agents to parallelize engineering work - breaking large tasks into agent-
• executable subtasks, managing context handoffs between agents, and coordinating outputs into coherent, production-ready deliverables. This is a core competency, not a bonus.
• Full-Stack Feature Ownership: Drive end-to-end delivery across Node.js backends and Next.js frontends, from schema design to production deployment.
• LLM Product Integration: Build and iterate on AI-powered product features - prompt pipelines, RAG architectures, structured output parsing, and agentic workflows embedded into clinical and consumer interfaces.
• Production Quality: Maintain high standards for API contracts, database schema migrations, CI/CD pipelines, and observability. AI-generated code is your code - you own its correctness.
• Compliance & Security: Ensure all systems meet HIPAA/SOC2 standards, focusing on data encryption, audit logs, and PII protection.

Backend & API:

• Node.js & TypeScript: Strong command of async patterns, event-driven architecture, and runtime performance.
• API Design: Proficiency in RESTful, GraphQL, and TypeSafe APIs (tRPC).
• Database: Solid PostgreSQL fundamentals (joins, indexing, migrations) and Redis for caching.

Frontend:

• Next.js & React: Working knowledge of App Router, Server Components (RSC), and client/server data flow.
• State Management: Experience with TanStack Query, Zustand, or similar.

AI & Infrastructure:

• LLM Integration: Hands-on experience integrating OpenAI or Anthropic APIs into production environments - streaming, tool use, structured outputs.
• Claude Agent Teams: Demonstrated experience building and orchestrating Claude agent teams using the Claude Agent SDK. You know how to decompose a problem, spin up specialized subagents, manage inter-agent communication, and stitch outputs back into a reliable, production-ready result.
• AI Dev Tooling: Daily active use of Cursor, GitHub Copilot, or equivalent. You have strong opinions about how to prompt effectively.
• Cloud & DevOps: Familiarity with AWS (EC2, RDS, Lambda, S3), Vercel, and GitHub Actions.

• 3+ years of professional software engineering experience.
• AI-Native Workflow: You can demonstrate, concretely, how AI has changed the way you write and ship software. Portfolio or examples preferred.
• Full-Stack Range: Comfortable moving between backend logic and frontend implementation without hand-holding.
• High Agency: Ability to operate in ambiguous environments, self-direct, and make high-leverage decisions without constant supervision.
• Communication: Professional proficiency in English for technical documentation and async collaboration.

• AI as Infrastructure: We don't treat AI as a feature - it's woven into how we build, test, document, and ship. You'll be in the right environment to go further than anywhere else.
• High Complexity: Work on hard engineering problems involving real-time data, complex clinical state machines, and high-stakes reliability.
• Direct Impact: Your code will directly affect patient outcomes and the efficiency of healthcare providers.