Descripción del puesto
About Fullscript
Weâre an industry-leading health technology company on a mission to help people get better. We started in 2011 with one simple idea. Make it easier for practitioners to access the products they trust so they can deliver better care.
That simple idea grew into a platform that powers every part of care. Today, more than 125,000 practitioners use Fullscript for clinical insights, lab interpretations, patient analytics, education, and access to high-quality supplements. Over 10 million patients rely on Fullscript to stay connected to their care plans and follow through on treatment.
We build tools that make care smarter and more human. Tools that save time, simplify decisions, and help practitioners stay closely connected to the people they care for. When everything they need is in one place, they can focus on what matters most: helping people get better.
This is your invitation.
Bring your ideas, your grit, and your care for people.
Join us and shape the future of care.
The role
Weâre hiring a Staff Machine Learning Engineer to join our AI team and help shape the next generation of Fullscriptâs AI-powered experiences. Youâll work on building innovative AI capabilities that help clinicians provide better services and help patients improve their health.
This is a senior individual contributor role for someone who can go beyond implementation. In addition to building high-quality systems, youâll help define technical direction, guide architecture decisions, and identify where AI can create meaningful value in clinical workflows. Youâll work with a high degree of autonomy and partner closely with engineering, product, analytics, and medical stakeholders to deliver scalable, reliable, and clinically useful AI experiences.
What you'll do
Lead the design, development, and deployment of production, multi-turn LLM-powered features, including summarization tools and clinician-facing conversational agents that support follow-up questions and reasoning over clinical context
Own backend services in Python that integrate LLM agents with Fullscriptâs platform and support reliable production use
Help define technical direction for prompting, grounding, safety, and orchestration strategies used across clinical AI workflows
Establish and improve evaluation approaches for LLM outputs, including accuracy, hallucinations, edge cases, and overall feature quality
Shape engineering patterns for model-related workflows, including testing, CI/CD, observability, and version control
Partner with medical, product, and engineering teams to identify high-value opportunities for AI and turn them into practical, scalable product capabilities
Work cross-functionally with engineering, analytics, and medical SMEs to refine requirements and ensure data and system design support clinical use cases
Provide technical leadership across projects by creating clarity in ambiguous problem spaces, guiding tradeoff decisions, and raising the quality bar for the team
Stay current with the latest LLM research and emerging AI technologies, and help assess where they can be applied effectively at Fullscript
What you bring to the table
6+ years of experience building and implementing machine learning applications in production, including meaningful experience with LLM-powered agents, conversational experiences, or agent-based workflows
A track record of owning complex technical problems end to end and shaping implementation beyond your immediate code contributions
Experience designing and deploying AI systems that answer open-ended questions, support follow-up interactions, and operate reliably in production
Strong experience with LLM application frameworks and tooling, such as LangChain, LangGraph, or similar orchestration and RAG frameworks
Familiarity with evaluation and monitoring frameworks for LLM outputs, conversational quality, and system reliability
Knowledge of MCP, agent orchestration patterns, or related approach