The Opportunity

We’re hiring a Senior Machine Learning Engineer to join our AI & Analytics Engineering team. This team builds AI-powered lab interpretation, clinician decision support, and conversational experiences directly into the Fullscript product.

You’ll help build the systems behind some of Fullscript’s most important AI experiences: AI-generated lab summaries, practitioner-facing conversational agents, and tools that help clinicians move from data to insight more quickly. The work is technical, product-minded, and deeply tied to real practitioner workflows.

This is a senior individual contributor role for someone who has shipped production AI systems, understands how to turn ambiguous clinical and product problems into working software, and can own work from early experimentation through deployment, evaluation, and iteration.

You’ll work closely with engineering, product, analytics, and medical stakeholders to build AI features that are reliable, useful, and grounded in the way practitioners actually deliver care.

What you'll do

• Design, build, and deploy LLM-powered product features, including lab result summaries, clinical workflow tools, and practitioner-facing conversational agents.
• Build backend services that integrate LLMs and ML models into Fullscript’s platform, primarily using Python, with increasing exposure to Elixir as the platform evolves.
• Develop AI systems that can support open-ended clinical questions, follow-up interactions, and reasoning over structured and unstructured healthcare context.
• Implement prompting, grounding, retrieval, and safety strategies that improve output quality, consistency, and clinical relevance.
• Build evaluation, testing, monitoring, and CI/CD workflows for AI features, including approaches for accuracy, hallucination detection, edge cases, and reliability.
• Partner with medical, product, analytics, and engineering teams to translate clinical needs into practical AI capabilities that can scale.
• Own AI systems end to end, from experimentation and prototyping through production deployment, iteration, and ongoing improvement.
• Contribute to architecture and implementation decisions for AI-powered analytics, lab interpretation, and clinical decision-support workflows.
• Stay current with fast-moving LLM, agentic AI, and applied ML ecosystems, while staying pragmatic about what is ready for production use.

What you bring to the table

• 5+ years of experience in machine learning engineering, applied AI engineering, backend engineering, or a similar role, with a track record of shipping production systems.
• 2+ years of recent hands-on experience building LLM-powered applications, including conversational agents, RAG workflows, tool use, or agentic systems.
• Strong backend development experience in Python, with solid SQL fundamentals and comfort working across data-heavy product environments.
• Experience integrating LLMs such as OpenAI, Gemini, Anthropic, or similar models into user-facing products.
• Experience with LLM application frameworks or orchestration tools such as LangChain, LangGraph, Hugging Face tools, or similar frameworks.
• Strong engineering practices, including Git, testing, CI/CD, observability, evaluation, and production monitoring.
• Experience evaluating and validating LLM-based applications for quality, hallucinations, correctness, edge cases, and reliability over time.
• Ability to work independently in ambiguous problem spaces, ask strong questions, make sound tradeoffs, and partner effectively with technical, product, medical, and non-technical stakeholders.

Bonus if you have

• Experience with Elixir, Phoenix, functional programming, or an interest in building with Elixir as Fullscript’s AI platform evolves.
• Experience building AI assistants, conversational agents, or decision-support tools in healthcare, clinical workflows, regulated products, or other high-trust environments.
• Familiarity with MCP, Langfuse, agent orchestration patterns, tool-calling systems, or multi-step AI workflows.